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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes well beyond them: it discloses the auth requirement ('sign-in or an API key'), the scoping to the key's organization and mode (test or live), newest-first ordering, page-at-a-time behavior, the per-item fields (state, nextAction), and nextCursor being null on the last page. That is substantive context the structured fields do not carry.

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?

Three dense, waste-free sentences cover purpose, inputs, returns, exclusions and auth. Minor deduction: the 'do not use' exclusion arrives after the return-value sentence, so the routing guidance is not as front-loaded as it could be.

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 return-shape burden and does so (pagination, ordering, per-item fields, terminal cursor). Combined with the auth note and the sibling routing, an agent has everything needed to call it correctly.

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 both parameters (limit with max/default, cursor) are fully documented in the schema, so the baseline is 3. The description only restates that limit and cursor are optional and that cursor comes 'from the page before' rather than adding format or constraint detail beyond 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 states a specific verb and resource ('the person's cases', 'the id of a case you do not have') and immediately scopes it against the closest sibling by naming evictions_get_case. An agent can distinguish this list tool from the get/create/update siblings without opening any 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?

It gives an explicit use condition ('when you need the person's cases, or the id of a case you do not have') and an explicit exclusion with the alternative named ('Do not use this when you already have the case id (use evictions_get_case)'). This is the when/when-not/alternative pattern in full.

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