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

Beyond the annotations (readOnlyHint=true, destructiveHint=false), the description discloses meaningful behavioral details: task text 'is used only for bounded local matching and is never persisted raw,' and the verification contract is 'short-lived.' This adds real context about persistence and scope that annotations do not carry. It slightly under-specifies side effects such as rate limits or external network behavior, giving a 4 rather than a 5.

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 tightly packaged sentences: the first front-loads the call-or-not decision, the second enumerates the return contract, and the third covers the privacy behavior. There is no filler, repetition, or restating of the title.

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?

Given a nested input schema, an output schema, and safety annotations, the description covers the core needs: when to invoke, what will be returned, the ephemeral verification contract, and the non-persistence guarantee. It stops short of describing the plan's downstream consumer workflow or caveats on open-world repo data, but nothing critical is missing for an unplanned call.

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 43%, so the description must partially compensate. It adds semantics for the task param ('used only for bounded local matching and never persisted'), and its mention of the 'analyzed-vs-checked SHA relation' clarifies the checked_sha param. However, it does not explain the repo-vs-package disambiguation or max_files/path_hints semantics beyond what the schema already says, leaving the description to add only modest value over the structured 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?

The description opens with a specific imperative — 'CALL before editing an unfamiliar public repository' — and then enumerates concrete deliverables (bounded reading order, relevant files, dependency consumers, test/verification obligations, checked-SHA relation). This names both verb and resource precisely and differentiates it from siblings like evaluate_dependency_change and check_dependency, which focus on versions or risk rather than up-front planning.

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 gives an explicit when-to-use condition ('before editing an unfamiliar public repository'), and the package parameter schema adds a clear exclusion ('to judge a specific VERSION rather than the package as a whole, use evaluate_dependency_change instead'). It does not enumerate when not to use it relative to the other siblings (analyze_repo, check_change_risk), but the primary trigger is unambiguous.

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