Get evidence card

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuine context beyond that: missing items error out, cards expose no local file paths, and selector precedence is applied. It stops short of describing the returned card's structure or how clips are sampled across the timeline, which matters since there is no output schema.

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?

Three front-loaded sentences: purpose, routing, then selector rules and error behavior. Nearly every clause earns its place, though 'revision-bound resource URIs' is a slightly opaque qualifier for a routing decision.

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 no output schema, the description carries the return-value burden and does sketch what a card contains plus the notable omission (no local file paths) and failure mode. What is missing is any sense of clip payload shape or how 'timeline-spread' sampling behaves when n_clips is specified versus defaulted.

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 each parameter is already documented, establishing the baseline of 3. The description does add real value by specifying the slug-vs-video_id precedence order and the at-least-one-selector rule not encoded in the schema, but it adds nothing about n_clips limits or profile trade-offs beyond what the schema states.

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?

States a specific verb and resource ('Build a saved item's evidence card') plus the card's contents (identity, summary hints, timeline-spread clips). It explicitly distinguishes itself from the sibling get_library_item by describing that tool's different output shape, so an agent can choose without opening either 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?

Gives a positive trigger ('when you need a selectable card profile or clip count') and names the alternative (get_library_item) with the condition that selects it. It also states an operational precondition — 'Supply at least one selector' — and the resolution order (slug first, then video_id).

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