start_filter_research

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

The annotations only declare it writes and is idempotent; the description adds the auth scope ('Requires research:run'), the return contract ('Returns job ID/polling guidance; does not poll'), the retention rule for operation_id on ambiguous failures, and the warning not to shorten dates or chunk limits. Notably it is consistent with idempotentHint=true and destructiveHint=false.

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 scope, then prerequisites, then failure handling and exclusions. Dense at ~90 words with some telegraphic phrasing ('State comparison settings and attempt budget') that costs a little readability, but no clearly wasted sentence.

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 13-parameter mutation with a nested rule object and no output schema, the description covers prerequisites, auth, idempotency and the return contract well. The remaining gap is parameter-level semantics for the majority of the undocumented fields, which an agent must infer from the raw 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 only 15%, so the description must carry the load; it partially does by distinguishing rule vs filter_id + revision, explaining operation_id retry semantics, and warning against shortened dates. But season, market, side, line, min_sample, phase and game_type receive no added meaning beyond their type/bounds.

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 (submit), resource (bounded historical frequency/outcome job) and a tight scope constraint ('exactly one native rule or saved filter ID plus revision'). It implicitly separates itself from live-stat siblings via 'Never ... substitute live stats', but never names a sibling tool outright.

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 an explicit prerequisite sequence ('Discover capabilities, units, coverage, completed dates, markets and worker readiness first') and behavioral instructions for the call ('State comparison settings and attempt budget'). It also rules out adjacent actions ('does not poll, save a filter or start tracking'), though it does not name which sibling to use for those instead.

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