List recordings

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

Annotations already cover safety (readOnlyHint=true, openWorldHint=true), but the description adds substantive behavior: newest-first ordering, the 20-item server cap, stateless pagination with nothing persisted between calls, and a security warning that recording URLs expose call audio. That is real context beyond the annotations; only rate-limit/error behavior is absent.

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?

Dense and front-loaded: purpose, filters, pagination contract, and the security caveat appear in a logical order with almost no filler. The single run-on paragraph and the redundant trailing 'Read-only' (already an annotation) keep it from a 5.

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 enumerates the returned fields, and it covers the pagination model, page-size ceiling, date filtering, account scope, and the sensitive nature of recording URLs. An agent has everything needed to call this list tool 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?

With 75% schema coverage the baseline is 3, but the description introduces 'page/per_page' as pagination parameters that do not exist in the schema, while the schema exposes only limit/offset. This mismatch can mislead the agent about which arguments are valid, and it adds nothing about offset semantics. The date-format repetition merely mirrors the schema patterns.

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 ('List call recordings'), scopes it ('on this account including its sub-accounts'), and specifies ordering plus the fields returned (recording_url, call_uuid, numbers, duration). This clearly separates it from get_call_recording, delete_recording and list_call_records without the agent opening a 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 usable operational context: optional from_date/to_date filters, a 20-per-page cap, and the requirement to pass pagination params on every call because state is not retained. It does not explicitly route the agent to siblings (e.g. get_call_recording for a single recording), so it stops short of the when/when-not/alternatives bar.

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