get_filter_research

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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds substantial behavior beyond them: frozen inputs, independent frequency and outcome stages that can partially fail, report expiry semantics ('Expiry is not an empty result'), and a polling cadence contract. None of this is derivable from the structured fields.

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 dense sentences, front-loaded with what the tool reads before the polling caveats. Each sentence carries real information, though the polling-cadence sentence packs several distinct rules (interval, backoff, stop condition, ID retention) that could be split for readability.

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 describing the result surface (status vs result, partial failures, expiry) plus failure/lifecycle behavior. With annotations covering the safety profile, an agent has everything needed to call this 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?

Schema description coverage is 0%, so the description must compensate for both parameters. It partially does: 'status or result' maps to the mode enum values and 'retain job ID' gestures at job_id, but it never explains the mode default, the UUID format requirement, or which mode yields which payload. Baseline 3 is appropriate given the partial coverage.

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 (Read) and resource (one owned research job), and enumerates what is returned: status or result, frozen inputs, independent frequency/outcome stages, partial failures, report expiry. This is clearly distinguishable from siblings list_filter_research, start_filter_research and cancel_filter_research.

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?

Gives concrete operational guidance: respect Retry-After, poll at >=5s (15s on unchanged work), stop foreground polling after 10 minutes and retain the job ID, and it explicitly states it does not resubmit or poll automatically. It does not name an alternative sibling (e.g. list_filter_research for enumeration), so it falls just short of a 5.

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