Get library item

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

Annotations already declare readOnly, idempotent, non-destructive, so the safety profile is covered. The description adds real context beyond them: bounded defaults, the 'exactly one selector' constraint, and that missing or stale evidence yields a structured refusal rather than silently failing. It stops short of describing the refusal payload or pagination behavior.

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 sentences, all load-bearing: purpose first, then usage routing, then the selector constraint, then the follow-up URI/refusal note. No repetition of schema or annotations.

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?

Without an output schema, the description names the returned artifacts (card, canonical card, excerpt, chunk URIs) and the refusal case, which is close to complete. Minor gap: it does not say how paging past the initial chunk is requested beyond following URIs.

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 baseline is 3. The description earns the bump by stating 'supply exactly one selector', a mutually-exclusive constraint the schema itself does not encode (required is empty and there is no oneOf), which materially changes how an agent calls the tool.

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 ('Resolve') and precise resource scope: one saved item into a bounded default Librarian card, canonical card, excerpt, and corpus-chunk URIs. It names the sibling tools it differs from (get_evidence_card, get_uoink_corpus), so an agent can place it without opening schemas.

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 an explicit trigger ('Use before quoting or paging through evidence') and routes to alternatives with their selection conditions: get_evidence_card for selectable profiles and clip counts, get_uoink_corpus for full local Markdown. It also states the follow-up pattern via read_library_resource.

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