proj_compile

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

With no annotations, the description carries the full burden. It discloses that the operation runs a compilation and validates connectivity/design errors, and notes the active-project fallback, but says nothing about cost/duration, whether it is cached or always rebuilds, whether it mutates project state or caches, or whether it can fail on invalid projects. That leaves meaningful behavioral gaps for a potentially long-running build step.

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 action and outcome, then supporting detail; short overall. The opening sentence and 'This runs the project compilation' are mildly redundant, but nothing is bloated and sections are clearly labeled.

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-value detail is not required (and the description's Returns note is a bonus). The parameter is fully covered. What is missing for a tool sitting in a dense cluster of compile/validate siblings is disambiguation — why call this rather than proj_force_recompile or design_validate — and any note about build cost or freshness.

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%, so the description must compensate, and it does: it explains that project_path is optional and that omitting it targets the active project — meaning the bare schema (nullable string, default null) does not convey. This is the key semantic for the single parameter.

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 and resource ('Compile a project to check for errors') and adds what compilation actually validates (connectivity, design errors), which is more than a restatement of the name. It does not distinguish itself from closely related siblings such as proj_force_recompile, proj_get_compile_freshness, or proj_run_erc, leaving an agent to infer which compile-like tool to call.

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 implied: you compile to find errors. There is no statement of when to prefer this over proj_force_recompile (forcing a rebuild) or proj_get_compile_freshness (checking whether a recompile is needed), nor when ERC is the better check. An agent can guess the context but has no explicit routing guidance.

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