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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavioral context the annotations lack: the exact response fields and an interpretation contract for kind values that tells the agent how to act on the output.

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 dense sentences, front-loaded with the return shape followed by the action semantics. No filler, no restatement of the title.

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 an output schema present and one fully documented required parameter, the description is nearly complete for a read-only diagnostic call. Enumerating the return fields is mildly redundant with the output schema, but the kind→action mapping is the piece the structured data alone could not convey.

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 single build_id parameter already documents the bld_… format from build. The description contributes no additional parameter syntax or format 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 resource and scope: a structured failure object {stage, code, kind, error_lines, hints} for a failed build. That is concrete and distinguishable from generic siblings like status. It does not explicitly name which sibling it replaces, keeping it just 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?

Usage is implied by 'for a failed build' and the description gives post-call routing for the two kind values (project → fix source, account → relay deep link). It never states when to call this versus siblings such as status or get_mac_job, so guidance is only partially covered.

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