AnyAPI

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

Beyond the readOnlyHint/destructiveHint annotations, the description discloses meaningful behavioral caveats: latency values are nullable trailing-30-day observations, p99 is not a maximum, and heavy:true entries produce large responses requiring callers to plan how they will invoke run_api. No statement contradicts 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?

Three dense, purposeful sentences: the first is front-loaded with the core purpose and deliverable, the second adds a latency caveat, and the third warns about heavy responses. No filler or redundant restatement.

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 output schema and the readOnly/destructive annotations, the description covers what the agent needs to select and invoke the tool correctly: return contents, a key statistical caveat, and handling for large responses. The remaining details, such as parameter formatting, live in the schema.

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 sku_id and context, including the detailed context-length and grammar rules. The description adds no new parameter-level semantics, hitting the baseline of 3.

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

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

The opening clause 'Get the full definition of one API by SKU' names a specific verb, resource, and exact identifier, and the rest of the sentence enumerates the concrete content (schemas, pricing, latency). This is enough to distinguish it from sibling list/search/run tools, even without an explicit 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 gives actionable guidance: inspect latency before choosing a client or MCP timeout, and for heavy:true entries pass fields/max_items/summary to run_api. It stops short of explicitly stating when-not-to-use get_api or naming the preferred sibling for other cases, so it earns a 4 rather than 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?

Annotations already mark the tool as read-only and non-destructive. The description adds useful behavioral context: the balance is tied to a specific Bearer-token key, and a valid key is required, indicating an auth-dependent lookup. This goes beyond the structured hints and does not contradict them.

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 states the action, resource, unit, and auth requirement with no filler. Information is front-loaded and every word earns its place.

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

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

This is a simple read-only balance lookup. Combined with the readOnly and destructive annotations, an output schema, and a fully documented parameter schema, the description covers the goal, auth mechanism, and prerequisite. Nothing essential for correct invocation is missing.

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 only parameter, 'context', is fully documented in the schema with word-count, perspective, and content constraints, so schema coverage is 100%. The description does not attempt to re-explain the parameter, and the baseline of 3 is appropriate since the description adds no parameter-level semantics beyond what the schema already provides.

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

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

The description uses a specific verb ('Get'), identifies the resource ('remaining wallet balance in USD'), and states the auth mechanism ('AnyAPI key supplied as a Bearer token'). This clearly distinguishes it from siblings like list_apis, get_api, or quote_api, so an agent can select it unambiguously for balance queries.

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 when to use the tool (whenever the remaining wallet balance is needed) and states the prerequisite of a valid AnyAPI key. However, it does not explicitly mention alternatives or when not to use it, leaving sibling differentiation to the agent's 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=true and destructiveHint=false, and the description adds valuable context: reading persistent state, guaranteeing no repeat of the paid dispatch, and describing polling behavior. This goes beyond what the annotations alone communicate and does not contradict them.

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, each earning its place: the operation, the safety/non-repeat guarantee, and the polling cadence. No filler, and the most important distinction is front-loaded.

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

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

Given the output schema, annotations, and simple two-parameter interface, the description adequately covers purpose, non-repeat behavior, and when to poll again. It does not describe the final-result path or explicitly contrast with read_result, but that is not essential for a status-inspection 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 the schema already fully documents request_id and context. The description references retryAfterSeconds and the origin of request_id, but adds no material parameter-level meaning beyond the schema's own descriptions.

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

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

The description names a specific action ('Inspect or resume') on a specific resource ('a durable AnyAPI request returned by run_api') and immediately clarifies that it reads stored state. This clearly separates it from run_api, which creates the request, and gives the agent a precise mental model of what the tool does.

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 explicit polling guidance: 'Poll again after retryAfterSeconds while status is queued or running.' It also implies the correct alternative avoidance by stating it 'never repeats the paid provider dispatch,' but it does not explicitly name alternatives such as read_result or run_api.

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. The description adds valuable behavioral context: cost characteristics ('stays cheap even across the whole catalog') and pricing unit semantics (maxUsd vs maxPer1kUsd). It does not contradict annotations and provides useful non-obvious details about output interpretation.

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 front-loaded with the core purpose in the first sentence. Each subsequent sentence adds distinct value (cost trade-off, pricing detail, routing). No filler or repetition; appropriate length for the complexity of the 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 that an output schema is present (no return-value elaboration needed), the description covers all essential agent-facing information: what the tool returns (summaries), its limitations (no descriptions/schemas), pricing guidance, the optional filter, and sibling tool selection. Nothing an agent needs to decide or call correctly is missing.

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% for both parameters (context and category). The description only restates the category filter ('Optionally filter by category') which is already documented in the schema. It adds no new meaning about parameter syntax or values beyond what the schema provides, so it meets the baseline without exceeding 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?

The description starts with a clear verb-resource pair ('Browse available AnyAPI APIs') and specifies the exact content ('lightweight summaries (id, name, category, USD pricing)'). It also explicitly names sibling tools ('search_apis', 'get_api') and states what this tool is NOT (no descriptions or schemas), fully distinguishing it from alternatives.

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 routing: 'Use search_apis for every ranked query, or get_api for one API's full schemas.' It also notes the optional category filter and the intended use case (cheap whole-catalog browsing). This gives clear when-to-use and when-not-to-use guidance without ambiguity.

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 goes beyond the annotations by disclosing that the quote is free, requires no key, does not execute or charge anything, and resolves pricing exactly as the run will. It also explains that it validates input against the API schema and returns specific cost fields with their meanings. Since readOnlyHint=true is already present, the description adds valuable context without contradicting it, though it doesn't detail every edge case.

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, front-loaded with the most important fact (free, no key, no charge/execute), and every sentence adds value: usage caveat, validation benefit, return fields, and a critical scaling warning. It is well-structured and avoids redundancy despite covering several key details.

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 an agent deciding whether and how to invoke this tool, the description covers the necessary context: when to use it, what inputs to provide, what it returns, and what not to do with the results. With a full input schema and output schema, nothing critical is missing.

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 each parameter. The description adds meaning by explaining that sku_id and input must match exactly what would be passed to run_api, and it gives context for the returned cost fields. It reinforces the relationship between parameters and tool behavior, though it doesn't describe the context parameter in 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 is specific and action-oriented: it states the tool quotes pricing for a run_api call before execution, with no charge or execution. It distinguishes itself from siblings like run_api and read_result by focusing on pre-run pricing, and explicitly mentions validation, making its purpose unmistakable.

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 tells the agent to use this tool BEFORE running run_api, to pass the same sku_id and input as intended for run_api, and to catch invalid_input for free. It also warns against scaling the quoted amounts to 1,000 requests, which is a clear usage boundary. This effectively separates it from run_api and other siblings.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is known. The description adds valuable behavioral context beyond annotations: results are cached for ~15 minutes, are private to the key, and an expired id returns result_expired requiring a re-run. It also discloses the jq sandbox limits (250ms/2MB budget). This adds transparency not present in 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?

The description is two sentences, with the key value proposition ('without re-running or paying again') front-loaded. It packs essential information—usage, parameters, caching, expiration, and sandbox limits—without waste. Every sentence earns its place.

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

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

Given the complexity (6 parameters, an output schema, and specific caching/expiry behavior), the description is quite complete. It covers the main use case, the optional reshaping parameters, and the failure mode. It doesn't detail the return format, but the output schema exists to handle that. The only minor gap is that it doesn't mention rate limits or other constraints, but those are likely covered by annotations or are not critical.

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 each parameter is documented in the schema. The description adds value by framing these parameters as tools for 're-shaping' the cached result and provides a concrete jq example. It also explains that fields use dotted paths (though the schema also mentions that). This goes beyond mere parameter listing.

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 access a cached result from a prior paid run without re-running or paying. It specifies the verb 'Dig deeper' and the resource 'a paid run', and contrasts with re-running, effectively distinguishing it from run_api. The mention of reshaping via fields/max_items/summary/jq adds specificity.

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 explains when to use the tool: after a prior run_api call, to re-shape or retrieve more data from the cached result. It explicitly says 'without re-running or paying again', implying the alternative is run_api. It also gives a condition for not using it: if the id is expired, it returns result_expired and advises re-running. It doesn't name other siblings like get_api, but the context is clear enough.

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?

Beyond the annotations' basic flags, the description discloses that reporting is free/non-charged, that request_id connects to stored runs and upstream error bodies, and that the agent should proceed with the task rather than pause for user consent. These are valuable behavioral traits an agent could not infer from the schema alone.

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 purpose, then conditions, then cost, then parameter hints, then behavioral directive. Every sentence contributes distinct guidance and there is no filler or repetition of schema field names.

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 reporting tool with six parameters and a full output schema, the description covers purpose, triggers, behavior, cost, and the most important parameter semantics. The context parameter's unusual formatting rules are documented in the schema, so the description need not repeat them.

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 the baseline is 3. The description adds meaningful parameter guidance: summary should be one line, request_id is the single most useful field and eliminates the need to paste payloads, and details are not to be filled with raw payload content. This raises it slightly above 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 opens with a concrete verb and resource ('Tell AnyAPI something is broken') and then enumerates specific triggering conditions—wrong/empty/malformed data, misleading errors, bad pricing/schema, failed retries. This clearly identifies the tool as bug reporting and differentiates it from general-purpose sibling tools like send_feedback by tying it to failing run_api calls.

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 when-to-use conditions with concrete examples and instructs the agent to file the report and continue without asking permission. It does not explicitly name an alternative tool for non-bug feedback, so the when-not-to-use guidance is only implied.

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?

Beyond the annotations (which already mark it as non-read-only and potentially destructive), the description discloses strict schema rejection, charging only on success, response-size context risks, and the semantic of p99 as an observation rather than a maximum. These are meaningful behavioral traits not present in 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 long (six sentences) but every sentence carries operational information: prerequisite schema lookup, strictness warning, timeout guidance, auth, billing, and response trimming. It is front-loaded with the core purpose, though slightly dense; a small amount could be trimmed without losing value.

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 7-parameter tool with a rich output schema, the description covers prerequisites, schema strictness, authentication, cost implications, timeout considerations, and response-size mitigation. The presence of an output schema means return-value details are not the description's job; nothing an agent needs to invoke correctly is missing.

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

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

The input schema already describes all 7 parameters at 100% coverage, so the baseline is 3. The description adds important semantics: inputs must be built from the schema because strict validation rejects unknown fields, and the response-trimming parameters (fields, max_items, summary) never affect cost. This exceeds the baseline but is somewhat redundant with the schema's per-parameter cost notes.

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

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

The description opens with a specific verb and resource: 'Execute an API by SKU with a normalized input payload.' This clearly distinguishes run_api from siblings like get_api (schema retrieval), quote_api (pricing), and list_apis (discovery), leaving no ambiguity about what the tool does.

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 explicit when-to-use guidance: call get_api first unless the schema is already read, and use quote_api first to see price and validate input without charging. It also directs the agent to inspect latency via get_api before setting timeouts. No rival tool context is left implicit.

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 the tool as read-only and non-destructive, so the description adds substantial behavioral context beyond that: it discloses ranking behavior, relevance scores, total counts, ranking type, heavy:true large responses, and the lack of input schemas. It also warns about the common failure mode of guessing inputs, which is valuable behavioral insight.

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 long but well-structured, front-loaded with the core purpose and then logically expanding to parameters, output, and critical usage warnings. Every sentence adds value; the length is justified by the tool's complexity, though it could be slightly tightened without losing meaning.

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 search tool with annotations covering read-only safety, the description covers all necessary aspects: when to use, how to combine parameters, output shape, and the critical caveat about missing schemas and the need to call get_api before run_api. It also mentions heavy:true entries and the alternative list_apis, making it complete for an agent to invoke correctly.

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

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

Although schema coverage is 100%, the description adds critical semantic details: it explains the combinatorial requirement (at least one of query/category/platform), that category/platform alone enumerate, and the limit's default and max. It also clarifies the meaning of the relevance and total fields in the output, enriching the parameter understanding beyond the schema's minimal descriptions.

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

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

The description clearly states the tool searches APIs by meaning and keyword across name, slug, and description, and returns matches with descriptions (schemas omitted). It explicitly differentiates from siblings by noting the lack of schemas and pointing to get_api for schema retrieval and list_apis for browsing, making its purpose unambiguous.

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

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

The description provides explicit when-to-use guidance: it explains that at least one of query, category, or platform must be provided, and that category/platform alone enumerate. It also distinguishes from get_api (for schemas) and list_apis (for browsing), and warns against guessing inputs for run_api, giving clear usage context.

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

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

Annotations indicate no readOnly, no idempotent, no destructive hints, so the description carries the burden of explaining side effects. It adds useful behavioral context ('Free, never charged', 'pass summary', 'use details'), but does not explicitly state that this creates a support ticket or feedback record, nor what the response contains. With an output schema present, the response shape is covered, so a 3 is fair.

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 front-loaded: it defines the tool's purpose in the first sentence, gives concrete examples of appropriate feedback, and ends with the sibling routing rule. It is slightly dense but every sentence earns its place. Minor structural improvement would be separating the parameter guidance from the purpose statement, but it is not bloated.

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 non-destructive, feedback-collection nature and a full output schema, the description covers the core context well: what kind of feedback is welcome, that it is free, how to structure the content, and when to use report_bug instead. It could mention whether the feedback is anonymous by default or what happens after submission, but those are minor gaps for a low-risk tool with a clear output schema.

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 adds meaningful value by explaining the intended split between summary and details, emphasizing that summary is one line, and by describing what fields like sku and request_id are useful for. Some parameter-specific nuance, such as the request_id guidance, lives in the schema already, but the description's guidance on using details versus summary strengthens the agent's ability to fill the fields correctly.

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 ('Tell') and resource (AnyAPI feedback), and explicitly distinguishes its scope: non-defect feedback about missing APIs, fields, docs, or task friction. It clearly differentiates from the sibling report_bug, so an agent can tell them apart without inspecting either 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?

The description gives explicit when-to-use context ('an API you wanted and could not find', 'a field missing', 'confusing docs') and an explicit alternative ('Use report_bug instead when something behaved incorrectly'). This is exactly the kind of routing guidance that lets an agent choose correctly between siblings.

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