caption_add

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

Annotations provide only readOnlyHint=false, so the description carries real weight and delivers: the insertion is tracked ('as tracked insertions'), the internal structure (SEQ field, hidden bookmark for cross-references), the dependency on fields.update to refresh the number, and the return value ('address of the caption'). This is substantial behavioral context beyond the single annotation.

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?

Front-loaded with the action and reasonably dense; each clause (tracked insertions, structure, refresh dependency, return value) carries information. The single long sentence is a bit packed with structural detail, but nothing is clearly wasteful.

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 correctly states the return value ('address of the caption') and covers the key mutation behavior and cross-reference workflow. It does not touch the optional params (dry_run, expect, author, tag), but the schema documents those, so the description is nearly complete for a complex 9-param tool.

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 high at 89%, so the schema already documents each parameter. The description restates the label options, text, and above/below placement, mapping to schema fields but adding no format or constraint detail beyond what the schema provides. Baseline 3 is appropriate.

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?

Starts with a specific verb and resource ('Add a caption paragraph'), names the placement scope (above or below a body paragraph), and details the exact artifact produced (label, SEQ field, text, hidden bookmark). An agent can distinguish it from nearby siblings like xref_add and toc_insert without opening any 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?

The mention that 'the number is refreshed by fields.update' implies a follow-up workflow, which is useful. However, there is no explicit statement of when to choose this tool over alternatives (e.g. xref_add for referencing, toc_insert), so usage is only implied.

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