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

Beyond the annotations it discloses the key behavioral traits: this is not a pure read (it queues an external research run), the staleness policy (records under a week are served as stored, older ones refresh automatically), that `fact` short-circuits the run, that a partial result is returned with a note on what is still filling, and that an active Whimbrel key is required. That is substantive cost/auth/side-effect context the annotations alone would not 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?

Purpose and output shape are front-loaded, and the policy details follow in a logical order. The run of short 'Pass X' sentences mirrors the schema rather than adding to it and costs a little density, but nothing is truly wasted.

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 carries the return-value burden and does so: it enumerates the record's sections and explains the partial-with-note case. Auth and refresh semantics are covered; the only real gaps are the undocumented `since` parameter and no sense of run latency.

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 already 100%, so 3 is the floor; the description goes slightly beyond by tying `domain` to the 'new company not on the list' case, tying `refresh` to overriding the auto-refresh rule, and clarifying that `fact` returns stored data without queueing. It omits `since` entirely, so it does not fully supersede the schema.

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?

It clearly states the resource: a full research record on one company (company facts, named partners, dated events, evidence, gaps), plus the side effect of queueing a run when stale or missing. An agent can tell it apart from a lightweight lookup, though it never names the sibling (`company`, `research_status`) that would be the obvious alternative for a plain lookup or a status check.

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 real selection cues: use it 'when the rep asks for one', pass `fact` to get a single stored fact 'without queueing a run', pass `refresh` to force a new run, and it explains the automatic refresh threshold (>1 week). What is missing is an explicit 'when not to use this / use X instead' against the many sibling tools.

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