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

Beyond the annotations (readOnly, idempotent, non-destructive, closed-world), the description discloses that the tool is strictly cache-only with no fetches, extraction requests or writes on this path, that results retain source quotes, and that only deterministic historical links are reported. It also pre-empts misinterpretation of the returned groupings as verdicts, targets or forecasts, which is behavior annotations cannot convey.

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?

The usage trigger is front-loaded and the return-shape paragraph earns its space, but the definition opens with a summary sentence that the next paragraph restates almost verbatim ('Use after get_filing_extract for an order, capacity or other supported event'), producing visible redundancy. Length is defensible for the content but could be tightened without loss.

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 usefully explains what comes back: prior-state context, retained quotes, and the event_family timeline and open_questions groupings. The remaining gap is the undocumented required `news_id`, which forces the agent to infer how to address the target event.

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 50%: `query` is well documented in the schema itself, but `news_id` is completely undocumented in both the schema and the description, leaving the agent to guess what identifier is expected and where to obtain it. The prose discusses output structure (event_family timeline, open_questions) rather than adding meaning to the two input parameters.

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 a specific verb and resource ('Return cached prior-state context for a canonicalized filing event') and positions the tool relative to get_filing_extract, making the retrieve-prior-state purpose distinguishable. It falls short of a 5 only because 'canonicalized filing event' and 'supported event' are never concretely enumerated, so the exact domain remains partly inferred from the example families (order, capacity).

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?

It gives an explicit trigger ('Use this after get_filing_extract when the user wants the earlier state behind an order, capacity or similar event') plus a negative stipulation that it does not infer price correlation, causality or conclusions. It does not route the agent away from adjacent siblings such as search_company_disclosures or get_announcement_bucket, so it is clear context without full alternative coverage.

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