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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and closed-world, so safety is covered. The description adds value beyond them by disclosing the return shape (one row per call with direction, duration, outcome, identity, and transcript/recording presence) even though no output schema exists. It stops short of describing pagination or the seat-scoping behavior.

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 sentences, zero waste: the first front-loads what the tool searches by, the second front-loads what it returns. Every clause earns its 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?

For a 10-parameter tool with no output schema, the description covers the primary filters and the return shape reasonably well. However, it omits transcript-text search ('query'), missed_only, line selection, and any pagination guidance, leaving real gaps for an agent to discover only in the schema.

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?

With 70% schema coverage, the schema already documents days, limit, since, until, number, and contact, and the description's filter list largely duplicates those. It omits notable parameters such as the transcript-word 'query', 'line', and 'missed_only', so it adds only marginal meaning over the structured fields.

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 verb ('Finds') and resource ('phone calls on this Widely seat'), and enumerates the filter dimensions (date range, direction, contact name, number). That resource noun cleanly separates it from siblings like search_contacts, search_messages, and search_numbers, though it never explicitly contrasts with the single-call sibling get_call.

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?

Usage is implied rather than stated: an agent can infer 'use this to find calls matching filters,' but there is no when-to-use/when-not guidance, no mention of when to prefer get_call for a single call, and no note on result limits or paging. Adequate but with clear gaps.

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