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

Annotations already declare destructiveHint=true, readOnlyHint=false and openWorldHint=true. The description adds real behavioral context beyond that: partial-patch semantics (only supplied fields change), the TOC exclusion, dry_run preview behavior, and that publication state is unaffected. It does not warn about data loss or explain the concurrency implications of expected_revision, so it is good but not exhaustive.

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 short paragraphs, front-loaded with the core semantics, and every sentence carries information (partial update, TOC boundary, dry_run, publication state). No filler, though the field-category list is a slightly compressed run-on.

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 tool with ~30 patch fields, no output schema and zero parameter descriptions, the description covers the essential mutation semantics, the sibling boundary, and dry_run. It is still incomplete on required-parameter meaning (expected_revision as an optimistic-concurrency token, catalogue_id) and on permissions, so an agent could call it correctly only by guessing at expected_revision.

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%, so the description carries the burden. It explains dry_run ('returns a preview without writing') and loosely maps the patch fields into categories (colours, bar, controls, sound, reading, logo, title, language, PDF), which helps orient the agent. However, the required expected_revision parameter (a 64-char hex token) and catalogue_id are never mentioned, leaving a critical concurrency parameter completely unexplained.

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+resource ('changes only the fields supplied') and enumerates the affected domains (colours, bar, controls, sound, reading, logo, title, language, PDF), and it explicitly carves out the sibling it is not, naming foliade_set_chapters as the owner of the table of contents. An agent can distinguish this from other update_* tools without opening the 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?

It gives a clear use context (partial edits to reader/metadata) and an explicit exclusion ('It never touches the table of contents, which belongs to foliade_set_chapters'), plus guidance that dry_run previews without writing. It stops short of explaining when to prefer dry_run vs a real write or other prerequisites, so it is not fully explicit when/when-not.

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