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

Annotations already cover readOnly/idempotent/non-destructive, so the bar is lower; the description adds genuinely useful behavioral facts — the evaluation is scoped to public information only and criteria are not persisted. It does not explain how conditions combine (AND/OR), what the response shape is (and there is no output schema), or how unsupported fields behave.

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?

Two compact clauses with the core comparison stated first and the scope disclaimers following. Zero filler, though the terseness is achieved partly by omitting necessary detail.

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 tool with a complex nested schema, 0% parameter documentation, and no output schema, the description is too thin: it explains what the evaluation is not, but not what a result contains or how criteria are interpreted. The agent is left guessing at the semantics of the returned evaluation.

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 0% against two required parameters, one of which is a deeply nested criteria object with four oneOf condition kinds (oneOf/presence/range/verifiedFinancials). The description adds only that criteria are request-scoped and unsaved; it never mentions projectPublicId or the condition model, so an agent must reverse-engineer 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?

The description names a specific action ("Compare request-scoped criteria with public information") but never states the object being evaluated — the project referenced by projectPublicId is only discoverable from the schema. It is distinguishable from get_opportunity/list_opportunities in spirit, but the subject of the comparison is left implicit.

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?

"Not suitability, verification or acceptance" is a useful explicit exclusion that prevents the agent from treating this as a diligence/verification tool. However, it names no sibling alternative (e.g. get_opportunity for full detail) and gives no positive when-to-use condition.

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