Fallback

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

With no annotations, the description carries the full behavioral burden and does disclose useful traits: it does not execute requests, does not verify undocumented fixes, and costs $0.002/call via x402. However, it omits prerequisites such as auth requirements, rate limits, and whether the returned 'safe next action' is advisory-only, which matters for an unannotated diagnostic tool.

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 sentences, tightly front-loaded with the purpose first, followed by when-to-use and then the limitations/pricing. Every sentence adds information with no filler or repetition.

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 5-parameter tool with nested objects, no output schema, and no annotations, the definition covers purpose, timing, and limits reasonably well. It still leaves gaps on how to populate goal/attempt/request and what the returned next-action looks like, which an agent calling it correctly would benefit from.

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% across 5 parameters (goal, error, attempt, request, response), so the description should compensate. It partially does by telling the agent to 'provide a status, response, or error text,' mapping to the response/error fields, but it says nothing about goal, attempt, or the request object's expected shape.

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 gives a specific verb+resource ('Diagnose a failed API, HTTP, MCP, or tool request') and states the output type ('return a bounded safe next action'). It implicitly separates itself from a repair/execution sibling by saying 'it does not execute requests,' though it never names the alternatives request_repair or source_route directly.

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?

'Use it after a request fails when the safe next step is unclear' gives a clear triggering context, and 'it does not execute requests or verify undocumented fixes' sketches the boundary of when it should not be relied on. No sibling is named as an explicit alternative, so routing among the sibling tools is still left partly 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?

With no annotations, the description carries the full burden and does reasonably well: it discloses the output posture ('smallest justified request changes'), an abstention behavior when evidence is insufficient, and a per-call cost with payment mechanism ($0.005 via x402). It does not state auth requirements or whether the returned changes are applied or advisory.

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 tight sentences, front-loaded with purpose then precondition, with the pricing sentence last. No filler, though the cost sentence could be trimmed for some audiences.

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?

Covers purpose, trigger, output posture, and cost, which is solid for a tool with no output schema. However, for a 7-parameter tool with nested objects and 0% schema description coverage, the absence of any parameter-level guidance leaves a real 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 0% across 7 parameters, so the description must compensate and largely does not. It hints at the schema/error inputs and at constrained request changes, but never explains goal, response, error_route, or the allow_url_change/allow_method_change constraints that materially change behavior.

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 and resource ('Repair a failed API or HTTP request') and scopes it to a defined evidence set ('only supplied schema and error evidence'). This distinguishes it cleanly from the sibling error_route, which classifies rather than repairs.

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 names the precondition and the sibling that triggers it: 'Use after error_route identifies a request-shape or input problem.' It also states an abstention condition, which functions as a when-not. It stops short of naming a full alternative path for non-request-shape failures.

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 disclosure burden, and it does well on two fronts: it states the cost model ("$0.02 USD per call via x402") and characterizes the return ("ranked candidate routes and bounded evidence"). It stops short of covering rate limits, auth requirements, or what "bounded evidence" concretely means.

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?

Four tight sentences, front-loaded with purpose before usage rules and price. Nothing is wasted, though "bounded evidence" is unexplained jargon that slightly dilutes the efficiency of the return-value 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?

For a six-parameter tool with no annotations and no output schema, the description should say more about what comes back and how the remaining inputs shape results. Purpose, routing guidance and pricing are covered, but return semantics and three parameters are left to the schema alone.

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 names and characterizes the three primary inputs ("a goal and optional publisher domain or start URL") but says nothing about max_candidates, require_official, or preferred_formats, and adds no format or constraint detail for goal (500-char cap) or domain. Adequate but with clear 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?

States a specific verb ("Find") and resource ("likely authoritative or machine-readable sources") with a clear triggering condition ("when you know what information you need but not where to retrieve it"). It is plainly distinct from the siblings error_route, request_repair and stop_search, though it never names them to reinforce the boundary.

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 says when to use it ("Use it before blind searching") and when not to ("Do not use it when you already have the correct source or only need reasoning over supplied context"). Both a positive trigger and a negative exclusion are stated, leaving nothing 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?

With no annotations, the description carries the full burden, and it does disclose meaningful behavior: it performs no searches, it does not prove universal absence, and it costs $0.003 USD per call via x402. That covers side effects, epistemic limits, and cost. It omits what the tool actually returns and whether there are minimum input requirements (e.g., at least one check), leaving some gaps for a 5-param tool.

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 tightly written sentences: purpose first, then the usage trigger, then the limits and price. Every sentence earns its place and nothing is padded.

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 complex, deeply nested schema with no annotations and no output schema, the description covers purpose, timing, limits, and cost but leaves the entire input contract unexplained. An agent can decide when to call it but not confidently how to fill checks, search_budget, or remaining_routes.

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% across five parameters, including a nested checks array and a search_budget object, so the description must compensate and largely does not. It gestures at 'scope already checked' and 'cost' but never explains goal, risk, the checks fields (method/result/authority/coverage/exhaustive), budget fields, or remaining_routes. An agent gets no guidance on how to populate the required check objects.

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 decision function: deciding whether another search or paid retrieval is worth its cost given scope already checked. It also explicitly disclaims what it is not ('performs no searches itself'), which helps an agent distinguish it from the retrieval siblings. It does not, however, explicitly contrast itself against error_route, request_repair, or source_route.

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 trigger ('after several search or source checks') and the decision context ('whether to continue or return a scoped not-found result'), which is actionable. It stops short of naming alternatives or stating when this tool should not be called instead of another sibling.

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