jev_prepare_evidence

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

The description adds valuable behavior beyond annotations by stating 'Pinned collection uses no model' and 'No arbitrary commands or source edits', clarifying model involvement and side-effect boundaries. It also mentions hash-returning behavior. Since annotations already provide safety hints, this additional context is sufficient without requiring auth or rate-limit details.

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 is three short sentences with zero filler. The core function is front-loaded in the first sentence, followed by two tight constraint sentences about model usage and side effects. Every sentence earns its place.

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?

The description covers the core purpose, optional behaviors, output concept (hashes), and key safety restrictions. The schema fully documents parameters, and no output schema exists to require further return-value explanation. It is sufficiently complete for an agent to invoke the tool correctly, though it could be more explicit about the exact shape of the returned evidence.

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 100%, so parameters are already well documented by the schema. The description adds some high-level context like 'explicit authorized file excerpts' and 'evidence with hashes', but it does not meaningfully elaborate on root, task, checks, labels, or sources beyond what the schema provides. Baseline 3 is appropriate.

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 states a specific action and resource: 'Collect explicit authorized file excerpts' and 'return evidence with hashes'. It conveys the tool's evidence-preparation role and distinguishes it from sibling tools by focusing on collection plus optional classification/verification, though it never names an alternative explicitly.

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 explains what the tool does but gives no explicit guidance on when to choose it over siblings like jev_verify or jev_review. 'Pinned collection uses no model' is a behavioral constraint, not a usage selector, and no exclusions or alternatives are mentioned.

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