Build Audit Report

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

Annotations declare readOnlyHint=false and destructiveHint=false but say nothing about paths or overwrite policy. The description adds two genuinely useful behavioral facts: paths resolve on the server machine (not the client), and existing files are refused rather than overwritten. That refusal behavior is non-obvious and directly affects invocation safety, though the description stops short of stating what a successful call returns or where the paths must point.

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?

Three short sentences, each carrying distinct information: what is written, where paths resolve, and the overwrite policy. Front-loaded with the action and resource, no filler or repetition.

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 covers return values and annotations cover the mutation profile, so the description only needs to supply the path and overwrite semantics it does supply. Minor omissions remain, such as the format default and whether the output directory must already exist, but the definition is sufficient to call the tool correctly.

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 must carry parameter meaning and it only partially does: 'audit JSON file' maps to the audit parameter and 'paths resolve on the server machine' adds real meaning for output. The format parameter and its enum/default ('both') are only obliquely referenced via 'XLSX and HTML', and it is unclear whether output is a file path or a directory.

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?

The description uses a specific verb ('Write') with concrete resources ('new XLSX and self-contained HTML reports') and names the input source ('local audit JSON file'). However, it does not distinguish itself from the near-identical sibling revit_build_report, leaving the agent unable to choose between them from the text alone.

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 only weakly implied by 'from a local audit JSON file' — the agent can infer a JSON input must exist first, but there is no explicit when-to-use, no when-not-to-use, and no mention of the obvious alternative revit_build_report. For a tool with such a close sibling, this is a meaningful gap.

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