record_evidence

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds real value by disclosing idempotency (same URI returns the existing record), but it leaves open whether the new payload's kind/quote/title/publisher are merged, ignored, or error, which is the critical ambiguity for a dedup-on-write 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 sentences, zero waste, with the core action front-loaded and the idempotency caveat immediately after. Nothing could be cut without losing information.

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?

An output schema exists, so return shape need not be described, but this is a 6-parameter write tool with four undocumented fields and no explanation of what evidence kinds mean or how dedup interacts with supplied fields. For a mutation tool with low schema coverage, the description is too thin.

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 only 33%: uri and quote are documented in the schema, while kind (an enum of web/filing/transcript/dataset/user_note), title, publisher, and published_at carry no explanation anywhere. The description adds zero parameter meaning, so it fails to compensate for the coverage gap.

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?

"Record a source" names a specific verb and resource, and in context (evidence = source material backing claims) it is distinguishable from record_claim and record_thesis. It does not explicitly state the contrast with those siblings, so it stops short of 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?

There is no when-to-use guidance and no mention of the obvious alternatives (record_claim, record_thesis). The only usage-relevant fact given is idempotency on re-recording, which is a behavior rather than a selection rule.

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