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

Annotations only declare readOnlyHint=true, so the description carries the rest: it discloses the returned fields, the CACHED/UNCACHED cache-state vocabulary, and the error/logs indicators. It also names the backing RPC (build.v1 BuildService/GetBuildSteps), though it doesn't mention pagination behavior on the read path.

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 compact sentences with the field list front-loaded and the chaining instruction second; the RPC provenance tag at the end is low-value but brief. No wasted prose overall.

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's enumeration of returned fields is genuinely necessary and present. The only gap is that the read-path pagination flow (page_token chaining) isn't reinforced in prose, though the schema covers it.

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%, so all four parameters (project_id, build_id, page_size, page_token) are already documented in the schema. The description adds no parameter-level detail beyond referencing the step digest as an output, 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 ('List the BuildKit steps of a container build') and enumerates the exact fields returned (name, digest, start/end time, cache state, error, logs flag), which cleanly separates it from depot_get_build and depot_get_build_step_logs.

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 a concrete workflow: 'Find the failing step here, then pass its digest to depot_get_build_step_logs,' which routes the agent to the correct sibling. It lacks explicit when-not guidance or mention of the pagination flow, but the primary usage condition is clear.

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