Perceptlayer

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

Goes well beyond the annotations: it discloses billing semantics (credits charged only on success, failed calls free), response truncation at 100,000 characters with the mitigation (paging/limit), and a full error taxonomy with the required agent reaction for each code (retry, wait, fix params, dashboard action, config fix). That is exactly the operational context readOnlyHint/openWorldHint cannot convey.

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?

Front-loaded with the core action and return, then cost model, then parameter guidance, then error handling, then truncation. Every sentence carries actionable information for an agent; nothing is redundant with the schema or title.

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 everything an agent needs for a free-form, open-world call: how to build params, what the result contains (credits used/remaining plus JSON), what every failure means, and how to avoid oversized responses. With no output schema present, the description adequately substitutes for 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?

Schema coverage is already 100%, so the baseline is 3; the description adds real value beyond the schema by stating that parameters must match exactly what get_endpoint lists and that array parameters must be JSON arrays. It does not explain the free-form params object's nesting/typing beyond that, keeping it at 4 rather than 5.

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?

"Run one endpoint and return its JSON response" states a specific verb (run/call), the resource (one data endpoint) and the outcome (JSON response). It also positions itself against get_endpoint by naming it as the source of parameter documentation, so an agent can tell the two apart without opening schemas.

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 establishes clear context: it is the execution step for an endpoint identifier that came from search_endpoints and whose parameters are documented by get_endpoint. It does not explicitly say when NOT to use it (e.g. batching multiple endpoints, or previewing parameters), so it stops short of a full when/when-not statement.

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 openWorldHint=false, but the description adds two behavioral facts the annotations do not: the call is free and requires no API key. That is real cost/auth context an agent needs when deciding whether to probe first. It stops short of describing pagination or rate limits, which keeps it from a 5.

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 sentences, front-loaded with what is returned, then when to call, then cost. No sentence is redundant and nothing is buried.

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?

There is no output schema, so the description carries the burden of describing return values — and it does, listing every field an agent would need to construct a follow-up call_endpoint invocation. Combined with the cost/auth note, nothing material is missing for this simple single-argument 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?

With a single parameter at 100% schema description coverage, the schema already explains that 'endpoint' is an ID sourced from search_endpoints with an example format. The description contributes nothing further about the argument's syntax or edge cases, 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?

States a specific verb and resource ('Get the full parameter list for one endpoint') and then enumerates exactly what comes back: name, type, required flag, allowed values and limits, example params, credit cost, tier. An agent can distinguish this read-only introspection tool from call_endpoint and search_endpoints without opening a 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?

'Call this before call_endpoint unless you already know the parameters' gives both the recommended sequencing and the explicit exception that skips it. The alternative (call_endpoint) is named directly, so routing is unambiguous.

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 openWorldHint=false, and the description still adds substantial context beyond them: cost ('Free; no API key needed'), the tier concept with its gating condition ('restricted' endpoints need the account's restricted-endpoint terms accepted), and the exact shape of the compact result set including credits per call.

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?

Front-loaded with the action and its scope in the first clause, then evidence, then the return contract. Four sentences, each carrying distinct load (purpose, urgency/scale, query syntax, return fields and cost); nothing is repeated from the schema or annotations.

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?

No output schema exists, and the description compensates by enumerating the returned fields (endpoint ID, name, HTTP method, credits per call, tier, required parameters), which is exactly what an agent needs to decide whether to call this or a sibling. Nothing material is missing for a 3-parameter read-only search.

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 carries the baseline; the description still adds value with four worked query examples ('amazon product reviews', 'zillow property', etc.) that teach the expected query phrasing. It does not mention the optional 'vertical' filter or the limit range, leaving those purely to the schema, which keeps it below a 5.

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 ('Find Perceptlayer endpoints') and immediately scopes it to a website or kind of data. It also distinguishes itself from siblings by naming get_endpoint and call_endpoint as downstream steps, so an agent knows this tool only locates, never fetches.

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 instructs 'search before calling' with the reason (1659 endpoints across 248 sources), which is a clear when-to-use rule rather than an implied one. It also names the alternative tools and the exact handoff value (endpoint ID) that selects them, completing the workflow routing.

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