Audit a folder of Spine projects

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

readOnlyHint=true already establishes the safety profile, and the description correctly stays consistent with a read-only audit. Beyond that it discloses two useful traits: per-skeleton granularity of results and that strict mode escalates validation warnings to failures. It says nothing about runtime cost on large folders, file-count/scan-depth limits, or how errors like unreadable files are reported.

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 what is audited and what the output looks like, with the strict-mode caveat parenthesized and the usage context last. Every clause carries information; the telegraphic phrasing ('Validate, rig QA and budget') is compact rather than padded.

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 rightly specifies the result shape (one ok/fail row per skeleton) and covers the strict flag, which is the highest-risk behavioral nuance. For a five-parameter, nested-schema audit tool it still leaves the page-size parameter, the filtering parameter, and the budget-limit fields unexplained.

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 only 20% and there are five parameters including a nested limits object, so the description must carry more weight. It does explain 'strict' (validation warnings fail too) and implies the 'folder' scope and the existence of budget limits, but 'max' (1-500) and 'onlyFailed' are never mentioned and the seven nested budget fields are undocumented beyond the schema's 'Device budget for pass/fail'.

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 specific verbs (validate, rig QA, budget), a precise resource scope (every .spine and skeleton .json under a folder), and the result shape (one ok/fail row per skeleton). The folder-level batch scope implicitly separates it from single-file siblings like spine_validate, spine_rig_qa and spine_budget, though none are named.

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?

"For release checks and CI" gives a clear usage context, so an agent knows the intended scenario. However, it never states when to use a single-file sibling instead (spine_validate, spine_rig_qa, spine_budget) or any exclusions, leaving the choice among near-duplicate siblings to inference.

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