list_builds

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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the 'Touches: reads only' line is redundant. What earns credit is the cost model ('three requests to Odoo.sh') and especially the caveat that the backend has only been observed to return 4 builds, so older data is out of reach regardless of `truncated`.

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?

Labeled sections ('Returns:', 'Touches:', 'Bounds:') front-load the primary action and then answer expected agent questions in order. Dense but every clause carries information; only the 'reads only' line is wasted against the annotations.

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?

An output schema exists, so return values need not be spelled out, yet the description still flags `truncated` and its unreliable semantics — the single most important thing an agent must not misread. Cost, bounds and the reachability limit are all covered for a moderate-complexity 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 0%, so the description carries the burden, and it does add real meaning: `limit` defaults to 4 and caps at 20, which the schema does not state. Project and branch are only implied ('a branch of a project') with no identifier format guidance, which is the remaining gap.

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 plus scope and ordering: 'List the latest builds of a branch of a project, newest first, with their status, result and commit.' This cleanly distinguishes it from sibling reads like list_projects, list_branches and get_build.

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 the scope rather than stated; there is no explicit guidance on when to pick this over get_build or wait_for_build. It does add one genuinely useful decision cue — that older builds are unreachable even when `truncated` says otherwise — which nudges it above a bare 2.

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