call_logs_read

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds real behavioral context beyond that: latency and transcript data on get are only available with mode="full", and transcripts on export require includeTranscripts=true — both are non-obvious side effects an agent would otherwise miss. It stops short of describing output shape or pagination termination 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?

Three compact parenthetical clauses, one per action, with the sibling-routing exclusion front-loaded at the start and end. Dense but every clause carries information; the nested quoting around mode="full" makes it slightly harder to scan than it could be, but nothing is wasted.

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 17-parameter branching tool with no output schema, the description covers the essential decision surface: what each action does, which options are action-specific, and where not to look. Missing is the per-action parameter applicability matrix and any note on what a call log record contains beyond transcript/latency, which would be needed for full completeness.

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 17 parameters and only 53% schema coverage, the description usefully maps the filter families (agent, type, phone numbers, date range, search) and pins down the mode/action interaction ("transcript and latency data only with mode="full"") plus export options. It does not resolve which filters apply to which action — e.g. whether page/limit are honored during export or whether search is list-only — leaving a meaningful gap on a 17-param tool.

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?

Opens with a specific verb and resource ("Read voice call logs of the workspace") and immediately delimits scope with the call types (web, inbound, outbound). It also names the sibling it excludes — "Chat conversations are in list_conversations, not here" — so an agent can separate it from the conversation tools without 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?

The three actions are given with the conditions that select them: list with filters and pagination, get with a callLogId for a single call, export for many calls in JSON/CSV. It also states the routing rule to the alternative tool for chat data, which is exactly the when-not guidance an agent needs.

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