project_runtime_evidence

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

With no annotations, the description carries the full burden. It adds useful behavioral constraints: exactly one result, bounded, tree-hash-bound, and a clear list of rejected artifact types. However, it does not disclose side effects, persistence semantics, error behavior, idempotency, or return value, which would matter for a registration-style mutation tool.

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?

Two dense sentences with no filler. The primary action and resource are front-loaded, and the rejection criteria are expressed compactly. 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?

For a mutation-like registration tool with no annotations and no output schema, the description is too thin. It does not define what makes an evidence tool 'available', what qualifies as a valid bounded result, what the tool returns or does on failure, or how the tree-hash-bound format should be supplied.

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 0%, and the description does not directly explain 'artifact' or 'project_root'. It indirectly characterizes the artifact as a bounded, tree-hash-bound result, but an agent still lacks guidance on the expected object shape, how project_root should be formatted, or how the tree hash should be represented.

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 concrete action ('Register'), a concrete resource ('tree-hash-bound result from an available manifest evidence tool'), and adds explicit exclusions ('No raw code, prompt, transcript, database write or durable receipt is accepted'). It is distinct from the sibling knowledge and project tools, though 'available manifest evidence tool' is somewhat underspecified, so it misses a 5.

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 implies when to use the tool: when you have a bounded, tree-hash-bound result from a manifest evidence tool. It also provides negative guidance by listing accepted input categories, but it never names an alternative tool or explicitly states what to use for raw code, prompts, transcripts, database writes, or durable receipts.

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