paper_visual

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered and the description need not repeat it. The description adds that output is rendered on demand ('on-demand original PDF page/crop'), which hints at server-side rendering, but it omits cost/latency implications, and the phrase 'exactly one' sits awkwardly against the schema's contact-sheet mode for 2-6 evidence IDs. With annotations covering the behavioral bar, a 3 is appropriate.

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?

A single front-loaded sentence with no filler or redundancy; the core promise (what is returned) leads immediately. It is efficiently sized, though its brevity veers toward under-specification for a 7-parameter tool.

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 partially carries the return-value burden by naming the returned artifact (image, PDF page, or crop), which is useful. However, for a 7-parameter tool with three distinct output modes (single image, PDF page, contact sheet), it never explains how modes are selected or what the contact-sheet return looks like, leaving real gaps.

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 100%, so every parameter (bbox scaling, asset path, scale cap, page_number, evidence_id, evidence_ids) is already documented in the schema itself. The description adds no parameter-level meaning beyond what the schema provides, which is the correct baseline of 3 when the schema does the heavy lifting.

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 gives a specific verb ('Return') and a concrete resource (an extracted image, or an on-demand original PDF page/crop), which is clearer than a bare image-fetch restatement. It does not, however, distinguish the tool from its siblings (paper_ingest, paper_search, paper_batch_search) or state why one would fetch a visual rather than search. Purpose is clear but sibling differentiation is absent.

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 or when-not-to-use guidance in the description; the only routing hints ('Prefer this for figures', 'preferred over repeated visual calls') live in the schema property descriptions, not the tool description. An agent gets no explicit condition for choosing this tool over paper_search or paper_ingest. Usage is only implied by the tool name.

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