Record deterministic JSON Pointer evidence

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

The description discloses meaningful behavioral traits beyond the annotations: it reads a repository-local file, resolves a pointer, creates a content-addressed receipt, and does not invoke external resources. This complements the idempotentHint and readOnlyHint=false 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 is a single efficient sentence that front-loads the core behavior and follows with a useful exclusion statement. There is no redundancy or filler.

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 the 100% schema coverage, the annotations, and the straightforward tool behavior, the description is largely complete. It explains the main side effect and scope, though it does not describe return values or explicitly route to the sibling evidrift_record for other evidence types.

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 the schema already documents all parameters. The description adds only general context about reading a JSON file and resolving an RFC 6901 pointer, which maps to jsonPath and pointer but adds no detail beyond the 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 clearly states a specific verb and resource: read one repository-local JSON file, resolve an RFC 6901 pointer, and create a content-addressed receipt. It also differentiates itself from the sibling evidrift_record by emphasizing determinism and the absence of URL, command, package code, or LLM invocation.

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 clear context for when this tool is appropriate: capturing evidence from a local JSON file via a JSON Pointer, with no external execution. It does not explicitly name evidrift_record as an alternative, but the exclusions in the last sentence effectively scope the use case.

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