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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds behavior the annotations cannot: results come back one line per case, or as a menu with counts when the result set is large — meaningful since no output schema exists. It doesn't say whether filters combine or how the menu threshold is chosen.

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 resource definition, then triggers, then filters, then return shape and follow-up — a sensible funnel. The filter enumeration partly duplicates the schema's own parameter list, which is the one sentence that doesn't fully earn its place.

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 burden of describing results and does so (one line each, or a counts menu), plus points to get_evidence for sources and figures. Missing only secondary details such as whether multiple filters are ANDed and any result cap, which are unlikely to block a correct first call.

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 100% and each parameter (size bands, task key, theme key, outcome enum, industry enum, employees) is already documented in the schema. The description only restates the filter dimensions as a list, adding no syntax or combination semantics beyond the structured fields — the correct baseline of 3.

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 — listing real companies that used AI — and enumerates the outcome taxonomy (measured, company-reported, went wrong, walked back) that defines what a 'case' is here. It also contrasts itself with the sibling get_evidence, which fetches the underlying story, so an agent can separate listing from deep retrieval without opening a schema.

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 trigger questions ('Who has done this?', 'What went wrong for others?') and an explicit next step: 'Fetch the ones you use with get_evidence'. It stops short of naming when to prefer find_practices (practices rather than cases), which is the main sibling ambiguity an agent would still have to resolve.

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