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

Annotations already declare read-only, idempotent, open-world safety, so the description is freed to carry domain semantics — and it does: Certified means exchange self-certification, not CFTC approval; Approval Pending/Approved are a separate route; dates can be re-dated after status change; topics are MORVS classification; a stay is not a finding of a violation. This is substantial interpretive context an agent cannot get from 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?

Front-loaded with the search operation and filter surface, then caveats. Every sentence carries distinct information (no filler), but it is a dense, long block with several legalistic asides; the reader must parse clause-heavy sentences. Efficient but not maximally crisp.

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 7-parameter, no-output-schema tool in a domain with real ambiguity (filing status vs approval route, stay vs violation), the description supplies the needed disambiguation and defaults. It stops short of describing the shape of returned rows or result ordering, but the essential call-correctness context is present.

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 schema already documents each parameter's type and enum. The description adds meaning beyond that: default-year shard behavior, that title search never touches withheld titles, and that the stay flag is not a violation finding — clarifying the semantics of the Boolean filter rather than just restating it.

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 ('Search event-type CFTC product filings in the MORVS Prediction Market Register') plus the exact filter dimensions (exchange, year, status, topic, stay remark, title substring). It also actively disambiguates from adjacent data — 'Filings are not markets, volume, users or odds' — so an agent knows this is not the prediction_market_exchange sibling.

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 usage context: default year is the latest published listed-year shard, withheld titles are 'never searched' and the agent should 'use the CFTC ID link for the source record.' It does not, however, explicitly name a sibling (e.g., prediction_market_exchange) and state when to prefer it, so the alternative-naming component of a 5 is missing.

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