Pushbuild Data APIs

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

Annotations already declare readOnlyHint and openWorldHint, and the description adds real context beyond them: returns JSON records, defaults to 25 items, ceiling of 500, and a per-record billing model charged against free allowance then credit. However, it never says where maxItems is supplied (it is not a top-level schema property, so it presumably lives inside params), and it omits error/failure behavior and whether partial results are possible.

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 dense sentences, front-loaded with the action and its prerequisite, followed by output shape, paging limits, and cost. Every clause carries information the agent needs; nothing is padding.

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 generic API-proxy tool with only two parameters and no output schema, the description covers prerequisite, return type, result volume, and cost. It leaves out failure modes and the exact location of maxItems, which are the only meaningful gaps.

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

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

Schema coverage is 100%, so the baseline is 3; the description earns above baseline by telling the agent that `params` values should be derived from describe_api rather than guessed. It also mentions maxItems, which adds meaning but muddies semantics since that field is absent from the declared schema properties.

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 ('Run one API'), and scopes it to a single API using parameters obtained from describe_api, which distinguishes it from search_apis and describe_api. The 'one' vs the sibling discovery tools makes the distinction inferable but never names an alternative explicitly.

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?

Implies—fairly clearly—a two-step workflow: call describe_api first, then pass its parameters here. It does not state exclusions (e.g., when to use search_apis instead, or what happens if the api id is unknown), so guidance is clear context without explicit when-not 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 already declare readOnlyHint=true and openWorldHint=true, so safety and openness are covered structurally. The description adds one genuine behavioral fact beyond them: the call is 'Free,' which matters for a paid-API catalog. It says nothing about error behavior for invalid ids, rate limits, or whether coverage/price can be null, so the added value is real but thin.

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?

One sentence plus a one-word cost note, with the returned content front-loaded and zero filler. The telegraphic fragment style ('Input parameters (JSON Schema), coverage and price...') is dense but slightly awkward as prose.

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

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

For a single-parameter, read-only lookup with no output schema, the description covers what is returned (parameter schema, coverage, price) and where the input id comes from. The only real gap is that it never explains the handoff to call_api, which an agent would need to complete the workflow.

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% and the schema already gives an example id, so the baseline would be 3. The description goes slightly beyond by tying the parameter's value domain to search_apis, telling the agent where a valid id originates rather than leaving it to guess.

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 exact resource (one API id) and the exact payload returned: input parameters as JSON Schema, coverage, and price. That distinguishes it from call_api (invocation) and search_apis (discovery), though it never names call_api as the contrasting sibling. An agent can tell what this tool yields 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?

The phrase 'one API id from search_apis' establishes the prerequisite workflow: ids come from search_apis, and this tool resolves a single id. It stops short of stating when to prefer this over call_api or what to do with an unknown id, so there is context but no explicit exclusions.

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 and openWorldHint, so the safety profile is covered. The description adds useful context beyond them — that results carry api ids, coverage summaries and price per record, and that the search itself is free — but says nothing about result ordering, limits on the open-world search, or behavior on zero matches.

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 the verb and resource, then the return shape, then the cost. Nothing redundant and no filler.

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 no output schema, the description correctly spends its words describing what comes back (ids, coverage, price per record) and notes the cost. For a two-parameter search tool that is close to sufficient; a note on how to act on returned ids would make it 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 coverage is 100%, so the baseline is 3, and the description earns an extra point by demonstrating the expected query style with three real keyword examples rather than just the schema's bare 'Keywords.' The limit parameter is left entirely to 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?

Uses a specific verb ('Find') plus a concrete resource ('Pushbuild data APIs') and three example queries that pin down what kind of search this is. It implies adjacency to describe_api/call_api by saying results include 'api ids', but never names the siblings, so differentiation is only inferred rather than 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?

The examples ('campaign contributions texas', 'restaurant inspections', 'sec 13f') make the intended entry-point usage clear by implication. There is no explicit when-to-use/when-not statement and no guidance on following up with describe_api or call_api once an id is found.

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