Project Check References

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 known. The description adds meaningful behavioral context: it loads a manifest and registry, checks every reference, and returns an {ok, problems} structure with the semantics of 'ok' defined. It also explains that broken references are reported here instead of failing later, which any agent needs to know. This goes beyond the annotations without contradicting them.

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?

The description packs a lot of information: the issue reference (#143 / D1), the four specific failure modes, the parameter meaning, and the return format. While this is useful, the enumeration is verbose and the issue number is arguably noise for an agent. It front-loads the purpose effectively, but the detail could be condensed without losing meaning. It is not excessively long, but it lacks the tightness of a 4.

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?

For a tool with one parameter, no output schema, and read-only annotation, the description is nearly complete. It explains the input format, what the tool checks, and the return structure with the meaning of 'ok'. It does not describe potential error conditions or how to interpret the problems array beyond 'ok is True iff every reference is live', but for a read-only check tool this is sufficient. The description covers the essential ground without requiring further inference.

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 0% for the single parameter, so the description carries the full burden. It clearly states 'project: path to the project.json container', adding a definition and expected format beyond the bare type string. This is sufficient for an agent to supply the correct value, though it could have elaborated on path resolution details. It compensates well for the missing schema description.

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 clearly states the tool checks reference integrity in a project, naming specific failure modes (moved/renamed/missing files, dangling item-refs, unknown components, naming-convention violations). It distinguishes itself from broader validation tools by emphasizing 'before a merge' and the 'chronic PDM failure mode', making its specific purpose clear. However, it does not explicitly name sibling tools for contrast, so it stops short of a 5.

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?

The description provides a clear usage context: use this tool before a merge to catch broken cross-file references, instead of letting them surface as a cryptic merge failure. It implies when to run it (pre-merge) and what it prevents, but does not explicitly list alternatives or when-not-to-use cases. The guidance is strong but not exhaustive, earning a 4.

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