inspect_project

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered for free. The description usefully frames this as a pre-mutation inspection, but adds nothing about cost, resolution failure modes (e.g. when BeatSaberDir cannot be resolved), or whether inspection touches the filesystem beyond the project. With solid annotation coverage, this is adequate but thin.

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 sentences, front-loaded with the verb and resource, followed by a dense enumeration of inspected artifacts and a closing usage rule. No filler or redundant restatement of the name.

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 explained, and the artifact list tells the agent what to expect back. The gap is on the input side: for a tool with a required 'project' argument and a 'configuration' modifier, saying nothing about either leaves an agent guessing at call syntax.

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% and neither of the two parameters is mentioned in the description. An agent gets no indication of whether 'project' is a path, a name, or an identifier, nor what 'configuration' (default Debug) controls in the inspection. The description fully leaves parameter meaning to an undocumented schema.

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 ('Inspect') plus resource ('.csproj') and enumerates exactly what is inspected: SDK style, target frameworks, references, BeatSaberDir resolution, manifest, assembly version, BSMT.Tasks presence and git state. That enumeration distinguishes it from narrow siblings like get_assembly_info or get_git_info, which cover only a slice of this.

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?

'Use this before changing anything' gives a clear workflow trigger for a read-only pre-flight check. It stops short of naming exclusions or pointing at narrower alternatives (e.g. get_git_info when only git state is needed), so it is clear context without routing.

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