code_check

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

Annotations already cover read-only/idempotent/non-destructive, so the bar is lower, and the description still adds real behavioral detail: unsupported languages return not_checked (exit 4), exit 3 signals an absent site, and the per-site vocabulary (exists/absent/unknown/not_installed/guarded). This is well beyond what the annotations convey.

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-loads the language coverage, which is useful, but the rest is compressed into telegraphic fragments ('Input: paths, diff (a revision; nothing: changes against HEAD), or snippet + as_path') that are hard to parse. Every element earns its place, but the structure is cramped and reads like notes rather than guidance.

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 carries the full burden of explaining results via exit codes and site statuses, which it does. It stops short of explaining some statuses precisely (guarded, not_installed) and the exact output shape, leaving minor gaps for a tool with five optional params.

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 100%, so the baseline is 3, but the description meaningfully supplements it: diff means 'a revision; nothing: changes against HEAD', snippet pairs with as_path, and deps switches to manifest-vs-import comparison. That default-behavior clarification is genuine added value.

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+resource: checking whether modules, names, methods, arguments and keys referenced by code 'exist in the project and its environment,' and names the exact languages covered. It is not tautological and scopes the tool well, though it never explicitly distinguishes itself from the vague siblings (analyze, project_query).

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?

Gives an implied use case ('For code you wrote or edited') and enumerates the three input modes (paths, diff, snippet + as_path), plus a one-line alternative-mode hint for deps. However it never states when to prefer this over siblings like analyze or project_query, and offers no exclusions beyond the language restriction.

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