Prepare one publication for human review

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the baseline is easy. The description still earns credit by enumerating exactly what will not happen — no pre-confirmation booleans, Gallery/Library/GitHub writes, or code execution — and by instructing to show the preview and the complete plan once, which is a real behavioral constraint not encoded in the annotations.

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, front-loaded with the read-only/preflight distinction and then the side-effect exclusions. Nothing is padded, though the opening sentence is terse enough to read as cryptic jargon rather than a plain statement of purpose.

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?

For a read-only planner with a very large nested schema and no output schema, the description should explain what the plan contains and what the human review/apply step looks like. It instead spends its budget on negative guarantees, leaving the agent without a clear picture of the plan artifact or how figure_library_apply_publish relates to it.

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 0% across four parameters, one of which is a deeply nested candidate object, so the description must carry more weight. It adds only marginal meaning, clarifying that titles should be bilingual (title/titleEn) and that a scientific question is proposed; it doesn't explain working-snapshot prerequisites, target enum values, or gateDecisions at all.

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 title 'Prepare one publication for human review' is clearer than the description, which opens with the jargon phrase 'Read-only proposal or exact Working preflight' rather than a verb+resource statement. It does convey the tool produces a plan/proposal without side effects, but among siblings like figure_library_plan_publish_working_revision and figure_library_plan_publication_pr, nothing in the text explains which of these is which.

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?

'Default local' and 'exact Working preflight' imply two modes and a default, which is some usage signal. But there is no explicit when-to-use, when-not, or named alternative among the many sibling plan_* tools, so the agent must infer routing itself.

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