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

Annotations only declare readOnlyHint=true. The description adds valuable non-obvious behavior: results are ordered newest first and the default status filter is running+queued, which materially changes what an unqualified call returns. No pagination or return-shape disclosure, so not a 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?

A single dense paragraph that front-loads what the tool does, then the filters, then the significant default behavior. No filler sentences; every clause carries information.

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 7-param list tool with no output schema and readOnly annotations, the description covers purpose, filters, defaults, and a prerequisite. It omits any mention of pagination behavior, which the description could tie to page_size/page_token, leaving a minor gap.

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 coverage is 100%, so the baseline is 3. The description still earns credit by adding the actionable tip that ['failed'] finds failures and the repo-prerequisite for pr, which go beyond the schema text, though most of the status-default detail is repeated from the schema.

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 (List) and resource (Depot CI runs) plus ordering (newest first), clearly distinguishing it from sibling verbs like get_run_status or get_job. It does not, however, name the sibling alternatives it is distinct from, so it stops short of a 5.

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?

Provides real selection context: the default status filter is running+queued, and passing ['failed'] surfaces failures; it also notes that pr requires repo. There is no explicit when-not-to-use guidance or direct reference to sibling tools, so it is strong but not complete.

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