audit_spec_completeness

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

No annotations, so the description carries the burden, and it does reasonably well: it names the rubric dimensions applied and the output shape (0-100 score plus surgical fix advice), which tells the agent this is a non-mutating analysis. It never explicitly states it makes no modifications or requires no auth, and gives no cost/latency expectations for large documents.

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?

Front-loaded with the verb and resource, then the rubric checklist and return value in one dense sentence. Nothing is redundant, but the single run-on sentence with an embedded five-item list is harder to scan than a short split would be.

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 correctly supplies the return contract (0-100 score, fix advice) and the checks performed, which is what an agent needs before invoking. Minor gaps remain around input precedence and document size expectations, but the core is covered.

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 the schema already explains content and filePath including the either/or constraint. The description adds only the word "text," hinting that raw content works too, but gives no size limits, format expectations, or precedence rules beyond what the schema states.

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 ("Audits") and resource ("specification document or text"), then enumerates exactly what it checks (buzzwords, error codes, Gherkin criteria, UI matrices) and what it returns. This is clearly a read/analysis tool, distinguishable from the generate_* siblings that produce documents.

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: feed it a spec to get a quality score and fixes. But there is no explicit when-to-use guidance, no exclusions, and no routing versus the generate_srs / generate_sdd siblings an agent could plausibly confuse it with. Also silent on what happens if both content and filePath are supplied.

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