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

Annotations already cover read-only/idempotent/non-destructive, yet the description adds substantial context beyond them: results are newest-first with typed IDs and bounded snippets, the search scope excludes transcripts and team comments, linked calls/requests are the same intake rather than two leads, and returned customer content is untrusted data that must never be treated as instructions. That last point is a meaningful safety disclosure no annotation conveys.

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-loads purpose and searchable fields, then stacks filtering, result shape, exclusions, routing, and safety notes. Dense but every sentence carries information; the closing "reads do not change records..." sentence partly overlaps the readOnly/destructive annotations, which is minor redundancy.

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 6-parameter search with an output schema, the description covers scope, filterable fields, result ordering/shape, exclusions, and escalation to detail tools, so an agent has what it needs. Pagination mechanics are left mostly to the schema's cursor/limit descriptions, a small residual gap.

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 67% and the description largely restates schema facts (query length, optional type/from/to, page controls) without adding format or behavior detail beyond them. It adds marginal value (e.g., from/to as a filter pair) but does not compensate for the schema gaps. Baseline 3 fits.

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 ("Find") and resource ("calls and service requests") and enumerates the matchable fields (customer name, phone, email, address, service, summary, intake text), which clearly separates it from the single-record siblings get_call/get_request it points to. It does not, however, explicitly distinguish itself from list_calls or list_requests, which an agent could plausibly pick instead.

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 input guidance ("Supply query (2–120 characters), optional type and from/to, and page controls") and explicitly routes the agent to get_call/get_request for full details. It also scopes what the tool won't match (transcripts, team comments). There is no explicit when-not-use statement relative to the list_* siblings.

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