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

Annotations already cover readOnly/idempotent/non-destructive, so the description's contribution is the billing behavior — it explicitly reassures the agent that reading does not consume credits, which is genuinely non-obvious and not in the annotations. It also notes results are paged and complete ('every returned field'), though it doesn't state what happens past the last page or how large pages can be.

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 short sentences with the core action front-loaded and zero filler. 'with every returned field' is slightly ambiguous phrasing that could read as a claim about completeness or about projection, but the text is otherwise tight.

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 tool with three required parameters, no output schema, and no annotation-level detail on pagination, the description leaves key gaps: where job_id comes from, whether paging past the end errors or returns empty, and what a 'paid result' record contains. The credit-cost note is valuable but not sufficient 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 0%, so the description carries the full burden, and it only gestures at pagination via 'in pages'. It never explains offset/limit semantics, the 500-row limit ceiling, or what a job_id is and where to obtain it — all three required parameters remain semantically undocumented.

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+resource ('Read already-paid results') and adds the scope qualifier that results are paginated. An agent can tell it apart from save_search_results and search_leads, though it never names those siblings explicitly and 'results' is only anchored to a search job via the job_id parameter.

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?

'Does not spend more credits' implies the when: use this after a search has already been paid for rather than re-running a search. However, no alternative tool is named, no precondition (job must be completed, job_id obtained from list_search_jobs/get_search_job) is stated, and there is no when-not guidance.

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