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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description adds real behavioral context beyond that: results are token-redacted ("without tokens") and scoped to one run rather than a log. It doesn't say what happens on a missing or revoked run, which keeps it below 5.

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, both front-loaded with the return shape first and the disambiguation second. Every clause carries information: scope, redaction, alternative tools.

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 three fully documented parameters, no nested objects, and no output schema, the description covers purpose, exclusions, and a return sketch (run plus descendants, tokens stripped). It stops short of describing the tree's shape or depth/pagination limits, a minor gap for a read tool.

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%; run_id, admin_key, and project_id are all documented in-schema, including the .env lookup rule for admin_key. The description adds no parameter-level detail, so the baseline 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 ("Returns one run and its delegated descendants") plus a material scope qualifier ("without tokens"). It also explicitly distinguishes itself from gate_run_timeline and gate_audit, so an agent can route 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?

Gives both the positive case ("use it to inspect delegation and permission state") and the exclusions with named alternatives: not gate_run_timeline events, and the project-wide log is gate_audit. Nothing is left to inference about when this tool is the right choice.

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