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

Annotations already declare readOnly/idempotent/non-destructive, yet the description adds non-obvious domain behavior: 'Requested times await business confirmation; New does not establish that follow-up is unfinished' and a prompt-injection warning that returned customer content is untrusted. It also discloses read side effects ('Reads do not change records, send messages, or confirm appointments').

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 purpose, then filters, then return shape, then safety notes — every sentence earns its place. The final read-only sentence partially restates annotations, but it extends them with 'send messages, or confirm appointments', so it is nearly all signal.

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 filtered, paginated list tool with an output schema, the description covers scope, defaults, ordering, pagination token, and the trust/semantics caveats an agent needs. Return fields are only sketched, which is appropriate since the output schema carries them.

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 only 57% with source/status/archived documented nowhere but enums, and the description compensates by naming each filter dimension and stating the unfiltered default. It also surfaces nextCursor for pagination, though it adds no syntax detail beyond the schema for from/to or limit.

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+resource ('List service requests'), the collection's origin ('captured from calls and public forms'), and the ordering ('newest first by creation time'). This distinguishes it from get_request (single item) and list_calls (calls rather than requests).

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?

Explicitly names the four filter dimensions (from/to, source, status, archived) and clarifies the default scope ('All states are included unless filtered'). It doesn't route the agent away from alternatives such as search_intake or list_calls, so it stops short of full when-not guidance.

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