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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely non-obvious context: results span all projects, are sorted newest first, and carry status/model/project columns, which matters since there is no output schema. It does not say whether the list is bounded other than by limit.

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 front-loaded sentence that packs scope, ordering and returned fields with no filler. Every clause carries information an agent needs.

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 one-optional-parameter read tool with an output schema absent, the description supplies the return-shape summary, which is the main gap. What remains unexplained is pagination behavior beyond limit and how far back 'recent' reaches.

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 the sole parameter's default (20) is documented in the schema, so the baseline applies. The description adds nothing about limit, such as ordering constraints or whether larger values are expensive, so it neither helps nor hurts.

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?

The description names a specific verb and resource (list AI builds), states the scope (across all projects), the ordering (newest first), and the fields returned (status, model, owning project). That is enough to distinguish it from get_build_status, which handles a single build, and from list_projects.

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?

'Recent' implies this is the discovery/overview call and the project attribution hints at cross-project browsing, but there is no explicit when-to-use, no statement of what it excludes, and no pointer to siblings like get_build_status or cancel_build. Usage is inferable rather than stated.

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