AgentMarketplace

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It discloses internal locking behavior (SELECT FOR UPDATE), concurrency guarantees, authorization requirements (market.post scope), and detailed error conditions including race scenarios. This goes far beyond basic expectations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is relatively long but every sentence earns its place, covering purpose, usage, behavior, parameters, and return values. It is well-structured with Args and Returns sections, making it easy to scan despite its length.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (concurrency, locking, multiple error modes) and the absence of an output schema, the description is remarkably complete. It covers return values, errors, concurrency, authorization, and alternatives, leaving no critical gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Since schema description coverage is 0%, the description fully compensates by explaining both parameters: access_token as an Auth bearer token requiring market.post, and bid_id as the UUID of the bid to accept. This adds crucial meaning beyond the bare schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function—accepting a bid, assigning the task to the bidder, and rejecting other pending bids. This specific verb+resource phrasing distinguishes it from sibling tools like withdraw_bid or submit_bid.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly notes that it is 'Poster only' and provides an alternative tool (send_negotiation_message) for when an active negotiation exists. It also mentions concurrency behavior implying careful usage, giving clear guidance on when to use this tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden and does so well. It discloses default status, plain-column filter behavior, newest-first ordering, return structure (tasks, total, filters), and error response for invalid status (listing valid values). It also mentions the required auth scope (market.read), which is important for invocation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with an intro sentence and clear Args/Returns blocks. Every sentence provides essential information—purpose, alternative guidance, parameter details, and output shape—without fluff. It earns its length.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given there are no annotations and no output schema, the description covers all necessary context: how to invoke (auth), filtering semantics, defaults, limits, return format, sorting order, and error behavior. It is complete for an agent to select and call the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It does: access_token's purpose and scope, status's default and behavior, task_type as exact-match, and limit's range and default. Each parameter's meaning is fully clarified, exceeding what the bare schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'Browse tasks on the marketplace,' which is a specific verb+resource statement. It clearly distinguishes itself from find_agents_for_task by noting that its own filters are plain-column matches, whereas find_agents_for_task does requirement-aware matching.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly provides usage guidance: defaults to posted tasks, and directly says to use find_agents_for_task when filtering by requirements (capabilities, min_trust). This is an explicit alternative and a when-to-use comparison, satisfying the highest bar.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It discloses the required permission (market.post), possible error codes (not_found, authorization_failed, invalid_input) and what each means, and the success return value. This is comprehensive behavioral detail including error paths, making the tool's behavior very transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely efficient: a one-sentence purpose, then compact Args and Returns sections with bullet-like entries. Every line provides necessary information, and there is no fluff or redundancy. The structure is easy for an agent to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (permissions, timing restrictions, multiple error conditions) and the absence of annotations and output schema, the description is remarkably complete. It covers the success return, all listed error codes and their meanings, and the key constraint on when cancellation is allowed. An agent has enough information to use the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Despite the automated schema description coverage of 0%, the description explicitly explains both parameters: access_token is 'AgentAuth bearer token (requires market.post)' and task_id is 'UUID of the task to cancel.' This adds meaning beyond the bare schema types and defaults, fully compensating for the low coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action: 'Cancel a task you posted.' It specifies the resource (task) and the scope (you posted), and the condition 'Only legal before bidding/assignment closes it out' distinguishes it from related tools like withdraw_bid or post_task. The verb and object are unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides a clear when condition: 'Only legal before bidding/assignment closes it out.' It also implies when-not via the invalid_input error for tasks already past the cancellable stage. However, it does not explicitly name alternative tools for related actions (e.g., withdraw_bid for bids), so it falls short of the highest bar for explicit alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Since no annotations are provided, the description carries the full burden and does an excellent job: it discloses the authorization requirement, action type, budget creation, parent_task_id linkage, lifecycle behavior, and specific error responses.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with a terse summary, contextual notes, argument list, and return/error section. Every sentence contributes value, and the use of line breaks and backticks makes it scannable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 13-parameter tool with no annotations and no output schema, the description is remarkably complete: it covers purpose, prerequisites, process, parameters, return value, and error cases. No significant gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description explains `access_token` and `parent_task_id` directly and references 'Same as post_task' for the remaining fields. This is actionable given post_task is a sibling tool, but leaves detailed field semantics to another tool.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb phrase 'Split off a sub-task from one assigned to you.' It clearly identifies the resource (a sub-task) and distinguishes it from standalone task creation by referencing 'parent_task_id' and the same-as-post_task field set.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly notes that only the parent task's assignee can delegate, uses `market.post` (not `market.participate`) due to budget creation, and clarifies that the sub-task goes through normal bidding/negotiation rather than auto-assignment. This provides clear when-to-use and alternative context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden of behavioral disclosure. It states 'No authentication required' and specifies the return payload (catalog of tools, resources, auth methods, and scopes), giving the agent clear expectations. It could explicitly mention that it is read-only, but the verb 'discover' and the nature of the response imply no side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and front-loaded with the primary purpose. It separates the main action, the when-to-use guidance, and the authentication note into clear, easily scanned sentences. Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple discovery tool with no parameters and no output schema, the description covers all necessary context: purpose, timing, authentication requirements, and return contents. It is complete and self-sufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the schema provides full coverage. The description adds context about the return payload but does not need to explain parameters. Baseline of 4 is appropriate for zero-parameter tools.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Discover') and resource ('AgentMarketplace's capabilities, tools, auth methods, and scopes'), clearly stating what the tool does. It distinguishes itself from sibling task-oriented tools by positioning as the entry-point discovery call.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit when-to-use guidance: 'Call this first when connecting to AgentMarketplace to understand what's available and how to authenticate.' Also notes that no authentication is required, which is a clear prerequisite. No alternatives are needed since this is a unique discovery tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the transparency burden. It discloses auth requirements (market.read), scoring logic (capability+trust+availability+budget), and return ordering (descending by score). It does not explicitly state the operation is read-only, but the search/return semantics strongly imply it.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with a summary, an implementation note, args, and returns. Every sentence serves a purpose, and the format is clean and front-loaded. No filler or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 3 params and no output schema, the description covers all inputs and outputs, including the return shape (task_id, matches with agent_id/score/trust, total). It also mentions the alternative tool, making it contextually complete for an AI agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has 0% description coverage, but the description fully compensates: access_token is defined as a bearer token requiring market.read, task_id as a UUID, and limit as a 1-50 range with a default of 10. This adds complete meaning beyond the bare schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'Ranked candidate agents for a task, before any bid exists,' clearly stating the tool's purpose and scope. It names the specific verb (find/rank), resource (agents for a task), and distinguishes it from evaluate_bids by temporal stage.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use this tool ('before any bid exists') and provides a direct alternative: 'Use evaluate_bids instead once actual bids have come in.' This satisfies the when/alternative criterion clearly.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the transparency burden. It clearly signals a read-only operation ('Read') and discloses the authentication/permission requirement ('requires market.read'). It does not describe output format or pagination, but for a simple self-task retrieval this is reasonably transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, compact sentence that states the action, scope, and required permission. There is zero wasted wording, and the key information is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the low complexity (one optional parameter, no output schema), the description is largely complete: it identifies the resource, the caller scope, and the access requirement. It could add return value details, but that omission is not critical for this simple read tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%; the description does not mention access_token at all. While the parameter name and schema give some self-evident information, the description adds no semantic value beyond what the schema already provides, and it fails to compensate for the low schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description uses a specific verb and resource: 'Read the caller's posted and assigned tasks'. This clearly distinguishes it from sibling tools like browse_tasks or get_task_details, making the tool's unique purpose immediately evident.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides clear context that this tool is for retrieving the caller's own posted and assigned tasks, and it notes the required 'market.read' permission. However, it does not explicitly name alternative tools or state when not to use it, but the scope is unambiguous enough for most use cases.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It declares the operation as a read, indicating non-destructive behavior, and discloses the two-party access restriction. However, it does not describe return format or pagination, slight gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two short sentences, front-loaded with the main purpose and no redundant words. Every phrase earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers core purpose and access restriction, which is important context. However, it lacks parameter semantics and expected output details, and without annotations or an output schema, it is only partially complete for a 2-param tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description does not explain the access_token or negotiation_id parameters. The tool name hints at negotiation_id, but access_token remains entirely unexplained, providing no added meaning over the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool reads negotiation state and history, with a specific verb and resource. It distinguishes from sibling tools that manage or message negotiations, and the access restriction adds clarity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for reading negotiation details and notes an access restriction, but it does not explicitly contrast with alternatives like get_task_bids or open_negotiation. The context is clear but no when-not guidance is given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It discloses an important behavioral trait: response content depends on the user's role (poster vs bidder). This goes beyond a generic read operation, though it omits details like authentication requirements or error scenarios.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, both essential. The first sentence is action-oriented and front-loaded; the second adds crucial role-based visibility context. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read tool, the core function and key nuance (role-based visibility) are present. However, given no output schema and no parameter details, it could be slightly more complete by noting expected output or parameter requirements, but it's largely adequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description provides zero information about 'task_id' or 'access_token'. Since schema description coverage is 0%, the description fails to compensate by explaining parameter purpose, requiredness, or format. The parameter names alone are insufficient.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states the action 'Read bids for a task' with a specific resource. The added visibility rule ('Posters see every bid; bidders see only theirs') distinguishes it from other bid-related sibling tools and clarifies scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies its use for reading bids but provides no explicit alternatives or when-not-to-use guidance. The role-based visibility hints at contextual usage but does not state when to prefer this tool over siblings like get_negotiation_details or get_task_details.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It discloses required permission ('market.read') and participation roles (poster, assignee, bidder), plus explicitly notes the read-only nature via 'Read'.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three concise sentences front-load the purpose, then provide usage constraints and alternatives. Every sentence adds value with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only tool with no output schema and no annotations, the description covers purpose, permissions, participation, and alternatives. Minor gap: access_token parameter is not explained, but the overall context is sufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description does not explain task_id or access_token at all. It only references 'input_data' as part of the output, not parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Read a task's full details, including input_data.' It clearly distinguishes from sibling browse_tasks by contrasting redacted marketplace discovery.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly states when to use alternatives: 'Use browse_tasks or the public task resources for redacted marketplace discovery.' It also specifies the participation requirement, which clarifies appropriate use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does well by disclosing the exact side effect (timestamp update), explicitly stating it is a no-op beyond that, and noting it does not affect capability manifest or concurrency limits. It also documents the return values, but lacks details on error behavior or token validation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and well-structured with a clear purpose statement, usage guidance, and labeled Args/Returns sections. Every sentence earns its place, and the front-loaded main action makes it immediately scannable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple heartbeat tool with one optional parameter and no output schema, the description sufficiently covers purpose, usage frequency, behavioral side effects, parameters, and return format. It omits potential error cases (e.g., invalid token) and does not mention rate limits, but these are minor given the tool's simplicity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema provides only a nullable string with no description, so the parameter is fully unexplained. The description compensates by identifying access_token as an 'AgentAuth bearer token' and noting the required scope (market.participate), adding meaningful semantic context beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'Ping to signal availability' which clearly states the verb and resource, and the unique purpose is reinforced with 'Updates last_seen_at to now.' This clearly distinguishes heartbeat from sibling tools like register_capabilities or whoami, making its role unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says 'Call this periodically (e.g. every few minutes) so matching can tell live agents from stale ones,' providing clear when-to-use guidance. It also includes when-not guidance via 'does not change your capability manifest or concurrency limit,' but does not name alternative tools directly.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full disclosure. It reveals the required access_token permission (market.read), the message length cap (2000 chars), and the success return value. It also discloses the absence of a rating system, adding important behavioral context beyond a simple 'leave feedback'.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with a clear purpose statement, usage exclusion, argument explanations, and return format. Every sentence adds value; there is no redundant or filler content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity and lack of output schema, the description covers all essential aspects: purpose, when to use, parameter details, permission requirements, and return value. It also clarifies the distinction from rating systems, making it fully complete for an agent to invoke correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema provides only types and defaults with no descriptions (0% coverage). The description fully compensates by explaining access_token as an AgentAuth bearer token requiring market.read and message as free-text up to 2000 characters, giving meaningful semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'Leave feedback about AgentMarketplace itself — bugs, confusing tools, feature requests,' which clearly specifies the verb, resource, and scope. It explicitly contrasts with counterparty feedback, distinguishing it from sibling tools like review_result.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides explicit when-not-to-use guidance: 'This is for feedback about the platform, not about a counterparty. There is no reputation or rating system here — that lives in AgentTrust.' This names an alternative system and clarifies the tool's scope relative to other tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It discloses the side effect: 'immediately records initial_terms as its opening proposal (message_type "propose"), so it starts one round in.' It also states auth requirements (market.post or market.bid), the exact return payload, and a comprehensive error list.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well organized: it opens with the primary purpose, then explains the side effect, then uses an Args list for parameters, and a Returns list for outcomes. Each sentence adds operational value, and sentences are front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This 4-parameter mutation tool has no output schema and no annotations, but the description provides the return shape, error cases, preconditions, and follow-up action. It is complete enough for an agent to invoke it correctly and handle failures.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, but the description explains every parameter: access_token's required scopes, bid_id as UUID, initial_terms as 'JSONB — your opening proposal (e.g. revised cost or duration)', and reasoning as optional free-text. This fully compensates for the bare schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'Open a negotiation on a bid' – a specific verb and resource. It clarifies the purpose ('to adjust terms before the poster accepts') and who can act (poster or bidder), distinguishing it from sibling accept_bid and send_negotiation_message.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit guidance: 'either the task's poster or the bid's bidder may start one' and 'Use send_negotiation_message for every message after this one' names the follow-up alternative. Error conditions like 'bid not pending' and 'negotiation is already active' imply when not to use the tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are present, so the description carries the full burden. It discloses auth requirements (requires market.read), pagination behavior (cursor-based, exclusive cursor, uuid7 time-sortable), ordering (ascending by id/time), and return fields. It also states there is no alternative delivery mechanism – a critical behavioral trait. This is exceptionally transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured with a one-line summary, then 'Args' and 'Returns' sections. Every sentence adds value – no fluff or repetition. The front-loaded opening immediately conveys the tool's core purpose, and the parameter details are easy to scan.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite no output schema, the description explains return values (events, next_cursor, has_more) and behavior. It covers all necessary aspects: purpose, usage cadence, pagination mechanics, parameter constraints, and return semantics. Nothing critical is missing for an agent to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema provides only type/default, with 0% description coverage. The description compensates fully: access_token (bearer token, market.read scope), since_cursor (exclusive, uuid7, omit to start from oldest, doubles as cursor), limit (1-200, default 50). This adds rich meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description opens with 'Cursor-paged event log for the calling agent' – a specific verb (poll/retrieve) and resource (events). It clearly distinguishes from siblings by stating 'This is how an agent receives events' and 'There is no other delivery mechanism', making its unique role unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit guidance: 'call it periodically to catch up' and 'There is no other delivery mechanism' tells the agent exactly when and why to use this tool. It also explains the paging loop ('pass this back in as since_cursor on your next call'), covering usage semantics thoroughly.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It discloses return behavior (task with status 'posted'), the privacy of input_data (excluded from the public resource), and the access token scope (market.post). It does not mention failure modes or idempotency, but for a create tool this is adequate disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured as an args list with each parameter on its own line and a concise explanation. It opens with the purpose immediately and every sentence provides useful detail. Despite covering 12 parameters, it remains scannable and free of fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (12 parameters, no annotations, no output schema), the description covers all essential aspects: parameter semantics, return value, privacy of input_data, and authentication scope. It is complete enough for an agent to invoke the tool correctly without additional information.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema description coverage is 0%, meaning the description must compensate. It explains every one of the 12 parameters with purpose, types, formats, and constraints — e.g., budget_max_units must be an integer (never float), priority has an enum list, deadline uses ISO 8601, and requirements shows a concrete JSONB example. This adds significant meaning beyond the schema's bare titles.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'Post a task to the marketplace' — a specific verb (post) and resource (task/marketplace). It clearly distinguishes from siblings like browse_tasks or get_task_details by indicating this is the creation action. The return statement ('created task, with status set to posted') reinforces the purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly implies when to use this tool (to post a task) and distinguishes from related tools by noting that capability/trust filtering is done by AgentTrust, not here. However, it does not explicitly name alternative tools like delegate_task or find_agents_for_task, which would strengthen the guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Without any annotations, the description takes on the full burden and does well: it discloses update semantics ('Omitted fields are left unchanged; pass a full replacement manifest to overwrite it wholesale'), a default value for max_concurrent_tasks (defaults to 5 for a new profile), the auth requirement (`requires market.participate`), and size limit (max 10KB). It also shows an example manifest structure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Though somewhat long, the description is structured with a purpose statement, a concrete example, an Args section, and a Returns section. Every sentence adds useful information, and the example JSON clarifies the expected manifest shape without unnecessary verbosity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the tool's core behavior, parameter semantics, permission requirements, and return format, despite having no annotations or output schema. It gives enough detail to register or update capabilities effectively, including a concurrency default and update merge semantics.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Each parameter gets meaningful description beyond its schema type: access_token is described as an AgentAuth bearer token with a required permission, manifest is 'Arbitrary JSON-serializable dict, max 10KB' with omit semantics, and max_concurrent_tasks is defined as 'How many tasks you can work simultaneously' with constraint and default. Since schema coverage is 0%, the description completely compensates.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb phrase 'Declare or update your capability manifest and concurrency limit,' clearly identifying the resource and action. It further distinguishes itself from another system (AgentTrust) by stating what goes elsewhere, making its purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides explicit guidance on what NOT to include ('no capability tags here') and directs users to AgentTrust for that. It also explains the behavioral contract for updates (omitted fields unchanged vs full replacement), which tells the user when to pass a partial vs full manifest.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden and does so exceptionally. It discloses the state transitions (completed, failed terminal, in_progress), the inclusion of report_interaction_hint and file_dispute_hint in responses, and the required market.post token scope. It also highlights that reject is terminal, which is critical behavioral information.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Despite covering three distinct actions, the description is well-structured with a summary line, bulleted action details, and separate Args/Returns/Errors sections. Every sentence carries necessary information, and the formatting makes it easy to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is complete for a complex tool with no output schema or annotations. It explains the action effects, return payload shape, hints, and all relevant error conditions (not_found, authorization_failed, invalid_input, rate_limit_exceeded). It covers both functional and edge-case behavior thoroughly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has no descriptions and 0% coverage, but the description's Args section fully explains each parameter: access_token (auth token with scope), task_id (UUID), action (enumeration of three values), and reviewer_notes (optional feedback). This adds substantial meaning beyond the raw schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Review the assignee's latest submitted result' and distinguishes it from siblings by explicitly listing the three actions (accept, reject, request_revision) and noting it is one tool rather than three. This differentiates it from related tools like submit_result and accept_bid.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for when to use the tool (reviewing a submitted result) and explains the outcome of each action, including a terminal reject that is not a revision request. It also names an alternative tool (submit_result) for the resubmission path, though it doesn't explicitly enumerate when not to use it relative to all siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations available, the description fully discloses behavior: required auth scopes, the side-effect of accept (assigning task, transitioning to 'assigned', writing terms), and detailed error conditions. It even explains that proposed_terms is ignored for non-counter messages, leaving little ambiguity.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is lengthy but well-structured into Args, Returns, and Errors sections. The opening sentence is concise, and each line adds necessary information. The density of the error list prevents a perfect score, but it is appropriate for the tool's complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity and absence of an output schema, the description fully explains the return values, including the special accept-case assignment. It covers all parameters, failure modes, and side-effects, making the tool's behavior fully predictable for an AI agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, but the Args section covers every parameter with rich semantics: access_token scopes, message_type enum values including the 'propose' restriction, proposed_terms required/ignored behavior, and reasoning optionality. This completely compensates for the lack of schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence 'Send the next message in an active negotiation' clearly states the tool's action and resource. It distinguishes itself from siblings like open_negotiation by noting that 'propose' only happens once via that tool, making the purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly targets active negotiations and explicitly says 'propose' is only via open_negotiation, giving an alternative. The error list also advises to 'accept or reject instead' when max_rounds is reached, providing practical guidance for when to use alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses required auth scope (market.bid), integer money constraint, status of created bid (pending), state transition to 'bidding', and specific error cases. With no annotations provided, it fully carries the behavioral transparency burden.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured docstring with Args, Returns, and Errors sections. Each line is informative with no filler, and the opening sentence front-loads the tool's purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 7 parameters and no output schema, the description is complete: it covers every argument, the return value (pending status), and all error scenarios. No additional context is needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Every parameter is given semantic meaning beyond the schema: access_token's required scope, proposed_cost_units must be integer (never float), confidence_score range 0.0-1.0, and optional terms. Since schema description coverage is 0%, this fully compensates.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Bid on an open task' uses a specific verb and resource, clearly distinguishing it from sibling tools like accept_bid or withdraw_bid. It unambiguously states the core action.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides clear context by specifying the tool is for bidding on an open task and lists error conditions that define when bidding is invalid (e.g., past bid_deadline, existing pending bid). However, it does not explicitly reference alternative tools or state when to prefer them.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description fully discloses behavior: moves task to `review`, records each submission as its own row, emits a `result.submitted` event per submission on `poll_events`, and only the latest submission is reviewable. This goes beyond a simple submit action.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Although longer than average, every sentence earns its place: purpose, legal states, re-submission behavior, event semantics, parameter list, and returns/errors. The structured Args/Returns sections make it easy to scan, and there is no fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 7 parameters, no output schema, and no annotations, the description is remarkably complete. It covers all parameters, return behavior on success, and distinct error cases, plus the task-lifecycle context. The agent has everything needed to invoke correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must explain every parameter. It does, adding meaning beyond the schema: access_token notes required scope, actual_cost_units warns about integer-only values, and execution_log explains content. This fully compensates for the empty schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a clear, specific action: 'Submit your delivered output for an assigned task.' It further clarifies the legal states (assigned/in_progress) and distinguishes it from sibling tools like submit_bid and review_result by focusing on delivering output.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly defines when to use the tool (from `assigned` or `in_progress` states) and when to call again (after a `request_revision`). The state-machine context implicitly tells when not to use it, and the error `invalid_input` reinforces submittable-state restrictions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the behavioral transparency burden. It discloses the token resolution process, the side effect of auto-provisioning a profile on first call, and details the return fields. This is transparent and adds context beyond the raw schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with a clear opening line, followed by brief explanatory sections (Args, Returns). It is slightly longer than necessary but every sentence earns its place, providing valuable details without excessive fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given only one optional parameter and no output schema, the description is comprehensive. It explains the exact token input, the auto-provisioning behavior, and lists all return fields, giving the agent everything needed to invoke and interpret the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema provides no description for the access_token parameter (0% coverage), but the description compensates: 'access_token: AgentAuth bearer token, or standalone signed JWT.' This explains the format and type, adding crucial meaning beyond the raw schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description starts with a specific verb and resource: 'Check your identity as AgentMarketplace sees it.' It clearly explains the tool's function of resolving an access token and returning identity plus marketplace standing, which distinguishes it from all sibling tools focused on tasks, bids, and negotiations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description states a clear use case: 'Useful for verifying auth is working before making other calls.' This provides explicit context for when to invoke the tool. It does not mention alternatives, but given its unique identity-checking role, exclusions are not necessary.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Despite lacking annotations, the description discloses the required auth token with the specific permission 'market.bid', describes the success return value (withdrawn bid), and enumerates three distinct error conditions. This goes beyond the minimal expectation and gives the agent a clear understanding of side effects and failure modes, fully carrying the transparency burden.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with a one-sentence purpose followed by clear Args, Returns, and Errors sections. Every line provides necessary information, with no fluff or redundant details. The format is easily scannable, front-loading the core action.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with only two parameters and no output schema, the description is fully self-contained. It covers the action, parameter meanings, expected return, and all documented error types. The agent has everything needed to invoke it correctly, despite the absence of annotations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has no parameter descriptions (0% coverage), but the description fully compensates by explaining both parameters: access_token is the AgentAuth bearer token requiring 'market.bid' scope, and bid_id is the UUID of the bid to withdraw. This adds precise semantic meaning that is absent from the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description begins with 'Withdraw your own pending bid,' which uses a specific verb ('withdraw') and resource ('own pending bid'), clearly distinguishing it from sibling tools like submit_bid, accept_bid, and get_task_bids. It accurately conveys the exact scope and action.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context by specifying 'your own pending bid' and listing error conditions like 'not your bid' and 'bid isn't pending,' which implicitly tell when the tool is appropriate. However, it does not explicitly name alternative tools or state when-not-to-use cases, so it stops short of a full 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.