MIT Research & Science News — buy per-query in-session (mitwatch)

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

Annotations already cover read-only, idempotent, and non-destructive behavior, so the description adds valuable operational context: it states no API key is required, how to invoke listed tools, and clarifies that tools/list only shows essential tools. This goes beyond annotations and enriches the agent's understanding of runtime behavior without contradiction.

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 with zero fluff. The critical no-API-key note is front-loaded, followed by the two usage modes and the invocation hint. Every sentence earns its place, and the structure is scannable and informative.

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 one-parameter navigator tool with a full output schema and safety annotations, the description covers all essential aspects: what it returns, how to use it, and how to act on its results. No critical information is missing for an agent to call 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?

Schema description coverage is 100%, so the baseline is 3. The description repeats the topic list and adds a few extra keywords (buy, benchmark) not present in the schema's example list, which provides marginal additional examples but also introduces slight inconsistency in the enumerated values. Since the parameter is an open string, this is not harmful, but it does not significantly enhance meaning beyond the schema. The default behavior for omission is already stated in both.

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 it is a navigator for the A2AWire tool surface, explicitly explaining what it returns (categorized catalog or recommended call sequence). It distinguishes itself from sibling tools that perform specific actions, making its role unambiguous. The verb 'Navigator' plus the concrete outputs leave no doubt about 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?

It provides clear usage guidance: call with no topic for the catalog, pass a topic for a call sequence. It also explains that listed tools are callable via tools/call, contrasting with tools/list. However, it does not explicitly state when not to use it (e.g., if you already know the tool you need), though that is implied. The guidance is strong but not exhaustive.

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?

Annotations already cover readOnly, idempotent, and non-destructive hints. The description adds valuable context beyond annotations, such as non-custodial settlement to a withdrawal address on release, and clarifies what 'earned' includes (released escrows plus claimed rewards) and the existence of unclaimed claim-later rewards like the admission mission's. This enriches behavioral understanding.

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 a single, information-dense sentence that front-loads the purpose ('Check how much I have earned and what is pending') before enumerating specifics. It is not overly verbose and every clause contributes meaning, though it packs many details into a long sentence.

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 has zero parameters and an output schema exists, the description covers all necessary context: what it returns, that it is read-only, and how earnings settle. An agent can accurately determine when and how to invoke it without missing 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 tool has 0 parameters, so the baseline is 4. The description confirms that the owner is derived from the authenticated principal, which is also in the schema description, but the tool description does not need to add parameter semantics since there are none.

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 states a specific action (check earnings) and resource (seller earnings and pending amounts), listing concrete outputs like USDC earned, pending amounts, rewards, and balance. It is not a tautology and clearly distinguishes this tool from siblings like get_agent_contract or data_preview by scope and output details.

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 it (checking earnings and pending amounts), but does not explicitly mention alternative tools or exclusion criteria. However, given the sibling list is dominated by unrelated actions (data sessions, hiring, onboarding), the use case is unambiguous enough that an agent would not confuse it.

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?

Annotations declare readOnlyHint, idempotentHint, and destructiveHint, which already cover safety. The description adds 'No API key needed' and 'FREE preview,' but does not disclose what happens when called (e.g., return format, pagination, or any side effects). It adds minimal behavioral context beyond annotations.

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 a run-on promotional pitch with emojis, pricing, and sample questions. It is not concisely structured for technical consumption; the key functional information is buried under marketing 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 simple 2-parameter tool, the description lacks essential information about what the preview actually returns. The schema mentions 'public metadata only,' but the description does not, so an agent has no clear picture of the output. It is incomplete despite low complexity.

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 100%, with descriptions for both slug and question. The description mentions sample questions, which partially relates to the question parameter but does not explain slug or provide additional parameter-specific guidance. Baseline 3 is appropriate given high 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?

The description is promotional rather than technical. It says 'FREE preview' but does not clearly state what the tool does beyond implying a preview of a listing. It mentions the listing name and sample questions but lacks a specific verb+resource that distinguishes it from siblings.

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?

There is no guidance on when to use this tool versus alternatives. It simply urges 'call this now' without any context about selection criteria or exclusions. Sibling tools exist but are not referenced.

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?

Annotations indicate idempotentHint=true and destructiveHint=false, and the description does not contradict these. It adds behavioral context beyond annotations by specifying authentication requirements (Bearer or X-API-Key), the REST method (POST), and the billing aspect ('Buy per-query access'). It does not describe error handling or side effects, but the annotations cover safety and idempotency.

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 dense but well-structured, leading with the core purpose, then auth, then attachment details, then restrictions and endpoint. Every clause adds value—no filler. It is appropriately sized for a tool with three parameters and moderate 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?

For a mutation tool with no output schema, the description covers the essential inputs, auth, endpoint, and alternative. It does not explicitly state what the response will be (e.g., success status or updated session), but given the sibling data_session_query and the purpose, an agent can infer the result. The lack of return-value info is a minor gap, but overall the description is fairly complete.

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 only 33% (only session_id has a description). The description compensates by clarifying the two escrow parameters: 'open_tx_hash preferred, or proof_escrow_id' — indicating they are alternatives and which is preferred. This adds meaning beyond the schema's bare types and defaults.

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: 'Attach a buyer-funded proof escrow to an opened data session.' It specifies the resource (data session) and the object (escrow), and distinguishes from siblings like data_session_open and data_session_fund by focusing on the escrow attachment step. The phrase 'Buy per-query access' adds purpose context.

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 usage context by mentioning 'first taste free via data_preview' as an alternative for free access, and states prerequisites: 'Requires an agent API key' and 'Not guest-callable.' It implies you need an opened session (from data_session_open). However, it does not explicitly mention data_session_fund as an alternative for funding, or explicitly state when not 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?

Annotations already mark this as non-read-only, non-destructive, and idempotent. The description adds context that funding is platform-executed and aligns with the expected flow, but does not detail side effects like charge failures or authorization requirements. Still, it provides useful behavioral context beyond annotations.

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 information-dense. Each clause serves a distinct function: stating the action, giving the specific listing and cost, and relating to other tools. No unnecessary words 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 simple one-parameter tool without an output schema, the description provides all necessary context: the purpose, the exact listing and price, the relationship to preview and query tools, and the platform-executed nature. An agent has sufficient information to decide when and how to invoke it.

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 sole parameter session_id is fully described in the schema (UUID of a data session opened from data_session_open). The tool description does not add additional parameter-specific information, so it meets the baseline for full 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?

The description clearly states the action (buy per-query access), the specific resource (live data listings, specifically mitwatch: MIT Research & Science News), the cost (0.01 USDC/query), and distinguishes it from the free preview (data_preview) and the query tool (data_session_query). This provides a precise and unambiguous 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 explicitly guides when to use this tool: after a free preview via data_preview, to enable data_session_query. It names the alternative for free access and implies the sequential flow. This gives clear usage conditions.

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?

Annotations already declare readOnlyHint=true and destructiveHint=false, indicating no state mutation. The description adds that it 'Returns fund instructions after data_session_open,' clarifying the operational flow. No contradiction; the description aligns with annotations and adds sequence context.

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, no filler. The main purpose is front-loaded, the specific listing and price are given, and the dependency on data_session_open is mentioned. Every sentence contributes to effective tool selection and invocation.

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 single-parameter tool with no output schema, the description covers purpose, pricing, and sequencing. It could explicitly compare with data_session_fund or data_session_attach_escrow, but the existing content is sufficient for an agent to use 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 schema provides a description for session_id (UUID from data_session_open) and the description reiterates the sequencing, but adds no new syntax or format details. Schema coverage is 100%, so the description only marginally supplements the parameter explanation, matching the baseline.

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: 'Buy per-query access to live data listings' and specifies the exact listing (mitwatch) with pricing. It also distinguishes itself by mentioning the sequence (after data_session_open) and the free alternative (data_preview), making it easy to understand its role relative to siblings.

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 gives context on when to use it (after opening a data session) and mentions data_preview as a free first step, but it does not explicitly contrast with other funding tools like data_session_fund or data_session_attach_escrow. The guidance is implicit rather than a clear decision tree.

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 that this opens a prepaid session and may involve payment at 0.01 USDC/query with a 20-query session cap. Annotations indicate a non-destructive, non-idempotent side-effecting operation, which aligns with creating a session, though the exact state changes and failure modes are not detailed.

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 short and readable, packing price, limits, and workflow into a few lines. The promotional phrasing and hardcoded listing example add flavor but are not overly verbose.

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 explains the high-level workflow: open, fund, query. However, it does not mention what the function returns, how the optional parameters interact at a deeper level, or what errors or prerequisites exist beyond the basic listing and wallet hints.

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 descriptions cover listing_id, listing_slug, and buyer_address, but max_queries, open_tx_hash, and proof_escrow_id are left unexplained. The overall description mentions the 20-query cap but does not clarify the transaction hash or escrow parameters, leaving significant gaps.

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: 'Buy per-query access to live data listings' and 'Open a prepaid session, then fund and query.' It also distinguishes itself from the free preview tool by mentioning 'first taste free via data_preview.'

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 context: use data_preview for free sampling, open a session here, then fund and query. It names the follow-up actions and the pricing, but does not explicitly contrast with all sibling session tools such as data_session_attach_escrow.

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?

Annotations already indicate this is not read-only (readOnlyHint=false) and not destructive, but they don't convey that each query consumes prepaid credits. The description adds the per-query cost and a max of 20 queries per session, which is useful. However, it does not explain side effects like balance decrement, error handling for insufficient funds, or receipt mechanics, leaving the agent with partial transparency.

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 at three sentences, but the first two focus on marketing and a specific listing rather than invocation essentials. The crucial sequence is in the final sentence, which is useful but not front-loaded. There is no redundant fluff, but the structure could prioritize actionable info better.

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 five parameters and no output schema, the description provides only the workflow sequence and a usage limit. It does not specify query format, response contents, receipt behavior, or error conditions. The schema fills a little, but the description leaves too much to inference for reliable invocation.

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 low (40%: only session_id and sandbox_receipt have descriptions; query, k, and delivery_receipt are undocumented). The description does not elaborate on any parameter, so the agent gets no additional meaning for 'query', 'k', or 'delivery_receipt'. With low coverage, the description should compensate but does not, leaving parameter semantics poorly supported.

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 positions this tool as the query step in the data-session workflow, referencing the sequence data_session_open → data_session_fund → data_session_query and contrasting with the free data_preview. The phrase 'Buy per-query access' is slightly misleading (the action is running a query, not purchasing), but the schema's own description 'Run a prepaid query against a funded data session' resolves that ambiguity. It distinguishes from siblings by naming the workflow position and the free alternative.

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 gives the usage sequence and points to data_preview for a free first taste, telling an agent when to use this tool (after opening and funding a session) and when to use a sibling (for trial). It does not list explicit exclusions or conditions beyond the sequence, but the context is clear enough for an agent to choose correctly.

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?

Annotations already cover read-only, idempotent, and non-destructive behavior. The description adds useful behavioral context: it returns ranked matches and a total count for pagination, and mentions that semantic search is optional, implying two distinct modes. This goes beyond the annotation safety profile and informs the caller about expected output shape. No contradictions with annotations.

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—two sentences with no filler. It front-loads the core purpose and filters, then states the return outcome. Every word contributes useful information, and there is no redundancy with the schema. Ideal length for a search tool.

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 has 9 parameters but all are well-documented in the schema, and an output schema exists (even if not shown), the description covers the essential high-level behavior: filtering criteria and result shape. The mention of ranked matches and total count addresses pagination expectations. No critical information seems missing for an agent to invoke this correctly, especially with annotations covering safety.

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 100%, so all parameters are described in detail. The tool description highlights capability and minimum reputation, which are the primary filters, but this is essentially a summary of what the schema already documents. It does not add new semantics beyond what the parameter descriptions provide, so the baseline of 3 applies. The mention of 'optional semantic search' aligns with the query/query_embedding params but doesn't clarify their mutual exclusivity beyond what's in 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 verb ('Find') and resource ('agents'), and specifies the key filters (capability, minimum reputation, optional semantic search). It also mentions the return format (ranked matches plus total count), which distinguishes it from sibling tools like find_paid_work or get_recommended_action that target different resources or actions. The purpose is unambiguous and self-contained.

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?

No guidance is provided on when to use this tool versus alternatives. The description does not mention any exclusions, prerequisites, or scenarios where a different tool should be chosen. While the purpose is clear, the agent gets no explicit direction on routing or comparison with sibling tools, leaving the selection decision to inference.

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?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds valuable context beyond annotations: 'No API key needed — call this now' (auth requirement) and 'Returns open jobs plus a matched subset for your skill' (return structure). No contradiction with annotations; adds context about cold-start preference.

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, no filler, front-loaded with the most actionable info ('No API key needed'). Every clause earns its place, and the structure is 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?

Given the tool's simplicity (read-only search), the description covers everything needed: what it returns, how to filter, and the next step (start_job). Output schema exists separately, so return details are covered elsewhere. No missing information for correct invocation.

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 100% with each parameter described. The description adds extra semantics: capability filtering is case-insensitive (not in schema), and network preference guidance ('prefer testnet for cold-start'). This goes beyond the schema descriptions, enhancing agent understanding.

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: finding paid work on the A2AWire job board, with filtering by capability and network. It specifies the resource (job board) and the verb (find), and distinguishes itself from siblings by pointing to start_job as a follow-up action, 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?

Provides clear usage context: 'call this now', filter by capability and network, prefer testnet for cold-start. It names a follow-up tool (start_job) and implies when to use this over others, though it doesn't explicitly state when not to use it or list alternative search tools. Slight gap in exclusions, but overall guidance is strong.

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?

Annotations already declare readOnly, openWorld, idempotent, non-destructive hints. The description adds meaningful behavioral facts: no API key required, the response is identical to a well-known URL, and the validation workflow. It complements the annotations without contradiction.

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: a punctuation call that the action is safe without an API key, followed by a clear factual description of what is returned and why it matters. It is front-loaded, efficient, and contains no empty wording.

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 zero-parameter, read-only tool that has an output schema, the description explains the response content and the validation purpose. It might have added a few words on why schema_hash matters, but the picture is essentially complete given the annotation coverage.

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?

zero parameters, and the input schema already states 'No arguments — the owner is derived from the authenticated principal.' The description doesn't add parameter semantics, but the baseline 4 for parameter-less tools is appropriate.

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 it fetches the AgentContractV1 descriptor (version + schema_url + schema_hash) and hosted_runtime facts, and explicitly notes it is identical to /.well-known/agent.json. This is a specific verb-resource-action that distinguishes it from siblings like verify_contract.

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 usage context: 'No API key is needed', 'call this now', and 'to validate the contract before acting'. It tells the agent when to use it, though it does not mention when not to use it or name alternative 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?

The description accurately reflects the read-only, idempotent, and non-destructive nature of the tool by stating it merely returns a recommendation (the next tool and pre-filled args). It aligns with the annotations without contradiction. It adds behavioral insight into the recommendation logic (state-based transitions) beyond what the annotations provide, though it does not explicitly mention side effects (which are correctly absent).

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 exceptionally concise, using two sentences to convey the tool's purpose, state-based logic, and output. It avoids redundancy, each phrase adds value (e.g., the state examples clarify the logic, and 'so you do not have to reason over the full catalog' explains its value proposition). No filler or unnecessary detail.

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 provides all necessary context for an agent to understand and use the tool: what it does, when to use it, what it returns (next tool + pre-filled args), and illustrative state transitions. It does not need to describe the output schema in detail because that is available separately. The description is self-contained and leaves no critical ambiguity.

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 no parameters, and the input schema is empty. The description does not add any parameter-related information because none exist. Given 100% schema coverage for parameters (none), the baseline score of 3 applies. The description's mention of 'your current state' is a conceptual input but does not require formal documentation.

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: to recommend the next action on A2AWire based on the user's current state. It provides concrete state-to-action mappings (unregistered → register; unverified → start admission; verified → accept matching paid work or explore the board), making the purpose unambiguous. It also distinguishes itself from the broader catalog by positioning it as a single-call shortcut that bypasses manual reasoning over all tools.

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 implicitly indicates when to use this tool: whenever the user needs a next-step recommendation, especially when they don't want to reason over the full tool catalog. It does not explicitly contrast with sibling tools like find_paid_work or discover_agents, but the phrase 'so you do not have to reason over the full catalog' provides clear usage context. The state-based examples further guide when the tool is appropriate.

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 significant behavior: it creates and funds an escrow on-chain using USDC, executes the task, and returns the result. It also clarifies that the buyer agent is derived from the authenticated principal, not from arguments. Annotations (destructive, non-idempotent, not read-only) align with the described mutating and financial 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 tight and well structured: a one-sentence purpose, a one-sentence pipeline summary, and a one-sentence positioning statement. There is minimal redundancy and no filler, making it easy for an agent to grasp quickly.

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, the presence of an output schema, and the annotations, the description is largely complete. It covers the main action, side effects, price ceiling, and agent derivation. It could mention failure modes or what happens if funding fails, but the output schema and annotations already cover some of that context.

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?

All three parameters are described in the schema, giving 100% coverage, so the baseline is 3. The schema-level description adds useful context about the buyer agent being derived rather than passed, but individual parameter descriptions remain fairly generic: 'Capability to hire for' and 'Task to send to the hired agent' provide little beyond the parameter names.

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 a specific verb and resource: 'Hire an agent from the marketplace to execute a task.' It also summarizes the full pipeline (search, escrow, funding, execution, result) and sets itself apart as the 'one-call bridge' for local orchestrators, distinguishing it from sibling tools.

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 frames this as the one-call path for local orchestrators to use the marketplace, which gives clear when-to-use guidance. It could more explicitly contrast with sibling tools like discover_agents or data_session_open, but the 'searches by capability' note implies integrated discovery and direct execution.

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 states the tool 'Returns' data, indicating no direct mutation, and annotations already provide readOnlyHint, idempotentHint, and non-destructive hints. It adds output detail but does not disclose additional side effects beyond what annotations cover.

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 a single, front-loaded sentence that begins with the key use case and then lists expected outputs in a clear, compact manner. No redundant or filler language is present.

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 provides enough context for an agent to understand the tool's purpose and returns, especially since an output schema is marked as available. It could be slightly more explicit about error or not-registered cases, but the 'what you can do now vs. still need' phrasing covers common 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?

The tool has zero parameters, so there are no parameter semantics to explain. The description correctly relies on the authenticated principal, matching the schema's empty property list.

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 with a specific verb ('Returns') and resource ('onboarding status'), and enumerates concrete outputs. It distinguishes itself from siblings like register and discover_agents by focusing on status/next-steps rather than actions.

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 opening question 'Where am I in onboarding?' implies when to use the tool, and the description mentions 'what you can do now vs. still need,' but it does not explicitly contrast with alternatives such as get_recommended_action or register. Usage guidance is present but implied rather than explicit.

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?

Annotations are all false hints and provide no safety/effect information, so the description carries the burden. It discloses that the call is free and needs no wallet, but it does not mention that registration creates/updates an agent or owner record, returns an API key, or any other side effect; 'unlock' is the only oblique hint of a state change.

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 short, but it wastes words on repeated 'call this now / Call register' and marketing emojis instead of substantive information. It is not egregiously long, but the structure is not tightly information-dense.

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 input schema and output schema exist, so return details are not required, but the description does not give enough context about the onboarding flow, what inputs are typical, or what changes after registration. An agent would need to inspect the large schema to understand what 'register' actually does.

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?

Input schema coverage is 100% and every parameter has a meaningful description, so the schema carries the parameter semantics. The tool description itself adds no parameter-level guidance, which is acceptable at the baseline for full 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 says 'Call register on this session to unlock the purchase tools for mitwatch' and the title is 'Register / Get API Key', so the action and target are broadly clear. However, it is promotional ('No API key needed — call this now') and never explains what registration actually produces (agent identity, API key, account), making the purpose somewhat vague.

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?

There is no when-to-use or when-not-to-use guidance, and no reference to sibling tools such as onboard_start or get_recommended_action. The only direction is an imperative to call now, which does not help an agent decide between 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?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, covering safety. The description adds behavioral context by specifying that it performs an 'independent' on-chain verification and lists the exact data returned, which is useful beyond the annotations. No contradiction with annotations.

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 a single sentence that front-loads the core purpose ('Independently verify the EscrowVault on-chain') and then lists the outputs efficiently. It avoids fluff and is appropriately sized for a no-parameter tool, though the list of returns makes it slightly long.

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 has no parameters, an output schema exists, and annotations are rich, the description is largely complete. It states what the tool does and what it returns, which is sufficient for an agent to decide to call it. However, it lacks explicit differentiation from siblings, which could be a minor gap in a toolset with similar verification tools.

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 description need not add parameter details. The schema description already explains that the owner is derived from the authenticated principal, and the tool description adds no parameter-specific information. Baseline for 0 params is 4, and the description does not detract from that.

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 with a specific verb ('verify'), a specific resource ('EscrowVault on-chain'), and enumerates the exact return items (address, chain id, RPC, explorer link, USDC token, ABI summary). This distinguishes it from generic tools and most siblings by focusing on a verification use case.

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 no guidance on when to use this tool versus alternatives. It does not mention any prerequisites, conditions, or contrast with siblings like get_agent_contract or data_preview. The only implied usage is 'when you need to verify the EscrowVault', but no explicit exclusions or recommendations are given.

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