Burs-IA

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false. The only extra behavioral signal is "No external contact," which merely reinforces openWorldHint=false, so the description adds little beyond structured data. No auth, rate, or side-effect detail is provided.

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?

It is short and front-loads the topic, which is good, but it is composed of telegraphic fragments rather than well-formed sentences, leaving meaning ambiguous. Brevity here shades into under-specification rather than clean conciseness.

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?

An output schema exists, so return values need not be explained, and annotations cover the safety profile. However, for a coordination/routing tool with ambiguous purpose, the description leaves the agent without enough to confidently choose it over the eleven siblings, so it is only adequately 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 100%, so the schema already documents both parameters (request as a public non-sensitive need, protocols as preferred interoperability protocols). The description adds nothing about parameter meaning or constraints, so baseline 3 applies.

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?

"Agent collaboration" restates the name/title rather than naming a concrete verb+resource, so the core purpose stays vague. The "Known target: prepare_outbound_invitation" line gives a directional hint about what it leads to, but an agent still cannot tell precisely what this tool itself does beyond routing.

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 points to a downstream target (prepare_outbound_invitation) and an approval path (human_bridge_request), which is partial when-to-use guidance. It does not clarify when NOT to use this versus siblings like capability_triage or discover_capabilities, so the routing is 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 cover the safety profile (readOnly, non-destructive, idempotent, closed-world). The description adds that this is an aggregate of named capabilities and policies, giving real context beyond the annotations about what the status encompasses.

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?

Brief and front-loaded, but the labeled fragments ('Capabilities:', 'Autonomy:', 'Send rules:') are terse to the point of ambiguity. The labels imply an enumeration but the meaning of each entry is unclear.

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 status/aggregate tool with an output schema, the description should say what the response covers and how it relates to the sibling names it mentions. As written, an agent cannot tell whether the named items are returned values, references, or something else.

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, so baseline 4 applies. The description correctly notes no inputs are needed by simply not listing any.

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?

States 'Overall Burs-IA status' — a clear resource but a vague purpose. It never specifies what 'status' actually returns or what question it answers. It also doesn't differentiate from siblings like discover_capabilities, which it references.

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 on when to call this tool vs alternatives. It lists discover_capabilities, human_oversight_policy, and outbound_gateway_policy as 'capabilities'/'rules' but never says whether this tool aggregates them or whether the agent should call those tools directly instead.

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, idempotentHint=true, openWorldHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavioral context beyond that: no target tool is executed, no credentials are needed, and the result is explicitly not a security certification.

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 compact clauses, front-loaded with the action and immediately followed by the routing rule. Every sentence earns its place; only the clipped 'Known MCP endpoint:' opening costs it the top score.

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?

With an output schema present, return values need no explanation, and the annotations carry the safety profile. The description rounds out the picture with scope limits and routing, leaving little missing for a 3-parameter, 1-required 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 100%, so endpoint, idempotencyKey and protocolVersion are already fully documented in the schema, including replay semantics and protocol-version behavior. The description adds no parameter-level detail beyond what the schema provides, so the baseline 3 applies.

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 and resource: retrieve a read-only verification report for a known MCP endpoint, and it explicitly distinguishes itself from the sibling discover_capabilities. The telegraphic 'Known MCP endpoint:' fragment is slightly clipped, so it falls short of the crispest 5, but an agent can confidently separate this from its 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?

It gives a clear selection rule: use this when the endpoint is already known, and use discover_capabilities to browse Burs-IA first. That names the alternative explicitly, though it does not spell out when-not conditions beyond that one routing hint.

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, idempotentHint, non-destructive, and closed-world, so safety is covered. The description adds meaningful context: 'public-safe opportunity metadata only' and that it does not spend money or contact anyone. It stops short of return format or rate-limit details, but those are less critical given the output 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?

Two sentences, front-loaded with the core purpose and then the key behavioral constraints. Every phrase earns its place 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?

With an output schema present and all parameters fully documented, the description covers purpose, usage context, and behavioral boundaries adequately. Nothing critical is missing 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 description coverage is 100%, and all three parameters have clear descriptions. The description adds no parameter-specific syntax, defaults, or formatting beyond what the schema already provides, so baseline 3 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 states a specific verb and resource: 'list paid opportunities already registered by WORKNET.' It also clarifies what it does not do, distinguishing it from write/apply siblings like prepare_mission. An agent knows exactly what this tool returns without opening the schema.

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 says 'Use this in ChatGPT to list paid opportunities,' giving clear usage context, and explicitly excludes actions like applying or claiming work. However, it does not name the specific alternative tools for those excluded actions, leaving some inference to the agent.

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, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description nonetheless adds real value by enumerating the exact side-effect boundary (no write, claim, application, acceptance, payment or contact) and flagging that binding action is gated by human approval and BURSIA TRUST.

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, front-loaded with the action, followed by the binding-constraint caveat. No filler sentences; the enumerated list of non-actions earns its space.

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?

An output schema exists, so return values need not be explained. The description covers purpose, side-effect boundary, and the approval gate; only explicit alternative-tool routing is absent, which is a minor gap for this complexity level.

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% and the single id parameter is fully documented with pattern and description, so the baseline of 3 applies. The description's phrase 'one paid WORKNET item' reinforces the parameter's intent but adds no syntax or format detail 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 states a specific verb+resource: 'Create a deterministic internal pre-contract mission preview for one paid WORKNET item.' The word 'preview' and 'pre-contract' cleanly separate it from siblings like bursia_worknet_task and bursia_worknet_paid_tasks, even without naming them.

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?

Usage is implied (run this before committing to a paid WORKNET item to obtain a non-binding preview) but no explicit when/when-not or named alternative appears. The negative scope (no write/claim/payment) helps an agent infer boundaries but does not route to 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 readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds meaningful context beyond them by labeling the output a 'public-safe canonical record', signaling the data is sanitized rather than internal detail.

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 tight sentence with no wasted words, and the retrieval purpose is front-loaded. It is efficient, though it packs the usage rationale into the same clause rather than separating concerns.

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?

With an output schema present, return values need not be explained, and the single fully-documented parameter needs no extra description. The description supplies sufficient context for a read-only single-record lookup, though it could name the sibling it precedes.

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%; the id parameter has a pattern, length bounds, and example already documented in the schema. The description adds no additional syntax or format guidance, so the baseline of 3 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?

States a specific verb (Read) and resource (public-safe canonical record for one paid WORKNET opportunity), which is clear. It implies single-item retrieval versus the plural sibling bursia_worknet_paid_tasks, but never names that sibling, so differentiation is only implicit.

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 phrase 'before deciding whether to prepare internal work' gives implied usage context, tying it loosely to the prepare_mission workflow. However, no alternatives are named and no explicit when-not guidance is provided, leaving the agent to infer when this beats the paid_tasks list.

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, idempotentHint, destructiveHint=false and a closed world, so the safety profile is covered. The description adds one genuinely useful behavioral fact — 'Does not execute the external action' — clarifying this is routing-only, but it says nothing about latency, side effects on downstream systems, or what the classification yields (though an output schema exists).

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 short fragments, front-loaded with the action and free of filler. The telegraphic style borders on under-specification, but every sentence points at something an agent needs (the action, two sibling routes, and the no-execution boundary).

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 single parameter is fully documented and an output schema exists, so return values need not be described. What is missing is enough substance about the routing decision itself — what qualifies as a 'bounded need' and what happens after triage — for an agent to be confident about invoking it versus the named siblings.

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?

There is a single parameter with 100% schema description coverage ('Public, non-sensitive request to classify.'), so the schema carries the semantics. The description adds no format, length, or content guidance beyond what the schema and its example already provide, making the baseline 3 correct.

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's opening 'Route a bounded need' gestures at triage/classification, and the title 'Triage a capability request' fills in the resource, but the verb is fuzzy and 'bounded need' is unexplained. It does name two siblings (discover_capabilities, bursia_verify_mcp), which helps an agent locate it in the family, but the core action (classify a request and return a routing decision) is only implied.

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?

'Browse: discover_capabilities' and 'Known MCP endpoint: bursia_verify_mcp' point to alternatives, implying a routing rule, but the condition that selects this tool over those siblings is never stated explicitly. The guidance is telegraphic and requires the agent to infer when triage is the right entry point.

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, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds no behavioral context beyond that — no indication of what discovery yields, whether results are scoped, or how the optional query affects output, despite having no difficulty saying so.

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?

Very short and front-loaded, which is good, but the second and third sentences are telegraphic fragments ("Bounded need needing a lane") whose meaning is unclear rather than economical. Brevity here costs comprehension instead of buying it.

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?

An output schema exists, so return values need not be explained, and the annotations cover safety. Still, the description never defines what a "capability" or a "lane" is, so an agent has only a partial mental model for when this tool is the right entry point.

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% for the single optional `query` param, and the description adds nothing about its syntax or effect. Baseline 3 applies when the schema fully documents the parameter and the prose does not enrich it.

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?

States a verb and resource ("Browse Burs-IA capabilities") but "capabilities" is left undefined, so the agent cannot tell what objects are actually returned or enumerated. It gestures at sibling tools rather than describing the operation, leaving the core purpose only partially resolved.

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 two fragments ("Known MCP endpoint: bursia_verify_mcp", "Bounded need needing a lane: capability_triage") imply routing to siblings under certain conditions, which is more than nothing. However the conditions are stated as cryptic nouns rather than explicit when/when-not criteria, so the agent must guess at the trigger.

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 annotations already declare readOnly, non-destructive, idempotent, and non-open-world behavior. The description adds only 'No contact/write,' which is consistent but largely redundant with those hints, and it does not discuss authorization, rate limits, or other operational 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?

The description is very short and front-loads the main purpose and routing clues. It is efficient, though its fragmentary phrasing slightly reduces clarity.

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?

Annotations and schema descriptions cover safety and parameters, and an output schema exists. The description still leaves usage conditions implicit, making it only adequately complete for an agent deciding when and how to call this 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 100%, so both parameters are fully documented in the schema itself. The description adds no parameter-level meaning beyond what the structured fields already provide.

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 'Human approval/review' and names sibling relationships, but it lacks a specific verb-resource phrase such as 'request human review of a bounded result.' An agent can infer the purpose, but it is not crisply stated.

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 routes the agent by naming 'agent_collaboration_request' as the agent peer and 'prepare_outbound_invitation' as a known target, and it excludes contact/write. However, it does not explicitly say when this tool should be chosen over those 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, idempotentHint, destructiveHint=false and a closed-world scope, so the safety profile is fully covered by structured data. The description adds no behavioral context at all - no indication of what the policy contains, how large it is, or when it must be consulted - so it contributes nothing beyond the 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?

It is very short with no redundancy, which is a plus, but it is written as three telegraphic noun fragments rather than sentences, so the structure is ambiguous and the most useful routing information is buried in the trailing clauses.

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?

An output schema exists and there are no parameters, so the description does not need to cover return values or inputs. What remains missing is why or when an agent should pull this policy, which is the one piece of context a terse policy-reader tool needs; the sibling pointers partially compensate.

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 takes zero parameters, so per the rubric the baseline is 4. There is no parameter semantics for the description to clarify, and schema coverage is 100%.

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 names the resource ('General autonomy policy') but uses a verbless fragment, so it never states the action (reading/retrieving the policy) even though the title does. The two follow-on fragments do carve out sibling domains, so the agent can roughly place the tool, but the core purpose statement is 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?

It explicitly routes two adjacent concerns to named alternatives ('Send rules: outbound_gateway_policy', 'Overall status: bursia_status'), which maps topics to tools and implies what this tool is for. It stops short of an explicit when-to-use/when-not statement for this tool itself, so it does not reach a 5.

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 annotations already establish that this is a read-only, idempotent, non-destructive, closed-world operation. The description adds a meaningful behavioral fact beyond those annotations: 'Sends require human approval,' which clarifies the human-in-the-loop requirement governing outbound sending.

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 front-loaded with the core resource and then gives two routing pointers plus an approval requirement in four short fragments. Every sentence earns its place, with 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 simple read-only policy tool with no parameters and an output schema, the description covers the key routing and approval context. It could be slightly more complete by explicitly stating that it returns the outbound gateway policy rules, but the title and output schema fill that gap.

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 and an empty object schema, so there is no parameter semantics to explain. Per the rubric, a zero-parameter tool receives a baseline of 4 when the schema requires no additional description.

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 the noun phrase 'Outbound send rules,' which identifies the resource but does not state a verb such as 'read' or 'return.' It does distinguish related siblings by naming human_oversight_policy and prepare_outbound_invitation, but the core action remains implied rather than explicit.

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 gives clear routing guidance: 'General autonomy: human_oversight_policy' and 'Prepare: prepare_outbound_invitation,' which tells the agent which sibling to use for related needs. It also states the approval condition for sends, though it does not explicitly say 'use this tool when you need outbound send rules.'

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 non-read-only, non-destructive, non-idempotent, closed-world, but say nothing about transmission. The sentence 'It does not send' adds a materially important behavioral fact beyond the annotations, though it omits side effects, the rejection of private/local targets, and any auth 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?

Roughly twenty words with no padding, and the routing facts are front-loaded. The fragmentary colon-clause style is compact but slightly cryptic, keeping it short of ideal clarity.

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?

With an output schema, full parameter descriptions, and annotations present, the description only needs to add routing and non-sending semantics, which it does. A note on why permissionBasis must be documented or what 'prepare' yields would have closed the remaining gap.

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 all five parameters are already documented, including the enum for permissionBasis and the digest-binding behavior of agentId. The description adds no parameter-level meaning, so the baseline 3 applies.

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 names a specific action (prepare) and output (a local invitation), and separates itself from siblings by routing 'known target' cases here. However, 'local invitation' is left unexplained and the phrasing is telegraphic, so the agent gets the verb and resource but not a plain statement of what the tool produces.

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 gives explicit selection conditions against two named alternatives: no target routes to agent_collaboration_request, human review routes to human_bridge_request. That is genuine when-to-use guidance, though no prerequisites (e.g. permissionBasis requirements) or when-not-to-use cases are stated.

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