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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower, yet the description still adds ordering (oldest first), per-message shape (author, text, time), and the auth requirement ('sign-in or an API key') that annotations do not express. It stops short of covering pagination or result-size limits for a potentially large message list.

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 trigger condition, then input, return shape, exclusion, next step, and auth in a tight sequence. Every sentence carries either routing or behavioral information; the ordering and 'own and team's' detail both earn their 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 correctly compensates by summarizing the return shape and ordering. Auth prerequisites, the sibling exclusion, and the natural next call are all present, so nothing an agent needs to invoke this correctly is missing.

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 the single `id` parameter is fully documented in the schema, including its pattern and origin (create_case/list_cases). The description only restates 'Input: the case `id`', adding no syntax or format detail beyond the schema, so the baseline 3 applies.

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 ('Returns the messages on a case') plus scope ('the person's own and the team's, oldest first'), which no sibling does. An agent can distinguish it from evictions_get_case_events without opening either 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 an explicit when ('when the person asks whether the Evictions API team has written about a case, or before writing to it'), an explicit when-not with the named alternative ('Do not use this for the case's events (use evictions_get_case_events)'), and a follow-up route ('Next: evictions_send_case_message to reply').

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