Extract claims

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

Annotations mark it non-readonly and non-idempotent, and the description corroborates this by stating it appends rows and returns their IDs, while clarifying that no truth determination happens here and that invalid entries are skipped and reported in errors. That is substantive context beyond the annotation flags, including an explicit scope limitation on model execution.

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?

Four short sentences, zero filler, with the core action and the sibling routing front-loaded before the behavioral caveats. Each sentence delivers a distinct, load-bearing fact with no repetition 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?

With only three parameters, full schema coverage, and annotations present, the description covers purpose, ordering, alternatives, mutation behavior, and the model-execution caveat. The one gap is duplicate handling: since the tool appends and is non-idempotent, it does not say whether re-submitting the same claim for a video_id creates a second row.

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 100%, so the baseline is 3, but the description adds real meaning: "Appends claim rows in extracted state and returns their IDs" explains the resulting state of the claims supplied, and "BYO model execution is not implemented" warns the caller not to expect mode=byo_key to run an actual provider model. It does not add syntax detail for claim_text or check_worthiness, which the schema already carries.

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?

Uses a specific verb and resource ("Store checkable claims ... extracted from a saved item") and explicitly positions itself relative to two named siblings, verify_claim and list_claims. An agent can distinguish this from the neighboring claim tools without opening a schema.

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?

"Use after reading its evidence" gives the ordering precondition, and the description names both alternatives with their selection criteria: verify_claim for supporting/conflicting evidence, list_claims for inspection. Both when-to-use and when-not-to-use are covered explicitly.

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