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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuinely useful facts beyond that: results are ordered newest first, what each record contains (outcome, duration, conversation), and an explicit redaction guarantee that request/response payloads are never returned.

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 short sentences, front-loaded with the ordering and content summary before the exclusion note. The first line only restates the title, which is mild redundancy, but the rest is dense with signal and no filler.

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 carries the burden of describing returns and does so in outline (outcome, duration, conversation, newest first) plus a clear statement of what is withheld. Pagination and error behavior live in the schema, so the remaining gap is minor.

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 description coverage is 100% and each parameter (limit, cursor, status, tool_id, agent_id) is documented in the schema with clamping, cursor reuse and 404/403 error semantics. The description adds nothing parameter-specific, so the baseline of 3 applies.

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 runs of a custom API tool) and immediately disambiguates the otherwise vague word 'runs' as 'the times the AI used the tool'. It distinguishes itself in substance from list_custom_api_tools (tools themselves vs. their executions), though it never names that sibling explicitly.

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 description gives no when-to-use or when-not guidance and names no alternative. An agent must infer from the noun phrase alone that this is for inspecting execution history rather than tool configuration; nothing routes it against list_custom_api_tools or get_agent_analytics.

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