komga_collections

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

Annotations already declare destructive/openWorld/non-idempotent, but the description adds real context beyond them: the confirm-gate mechanics, dry-run default behavior, the explicit list of high-risk action categories that trigger extra warnings, secret redaction in output, and the self-hosted-only constraint. The only blemish is the '5 operations' count against six enum values, a minor inconsistency rather than a contradiction.

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?

Dense but efficient — five sentences covering auth, write gating, dry-run, and the destructive list, with no filler. Front-loading is weak: it opens with a vague toolset statement rather than the write-safety rule, and the long warning enumeration is a comma 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 6-parameter destructive dispatcher with no output schema, the description covers the safety model well but leaves the action semantics unexplained — an agent cannot tell from the text what delete destroys (a collection? its entries?), how get differs from get_id, or what patch/post expect in body. Delegating detail to 'action help' mitigates but does not close the gap.

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 the schema already explains body, query, params, target, and confirm (including the rejection of false and the string 'true'). The description repeats the confirm rule but adds nothing about body/query/params structure or what path parameters like seriesId the collections endpoints expect. Baseline 3 applies.

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 names the resource (collections) and enumerates the actions (delete, get, get_id, patch, post) plus help, which lets an agent place it against siblings like komga_books or komga_series. But the opening 'covers the collections toolset (5 operations)' restates the name and miscounts (six enum values including help), and it never says what a collection is or what get vs get_id does. Purpose is inferable, not stated.

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?

Strong operational guidance: it names the auth mechanism, states writes require confirm=true plus KOMGA_ALLOW_WRITES=true, explains that omitting confirm yields a no-op dry-run, and points to 'action help with target' for per-action parameters. What's missing is routing guidance against siblings, though the resource name largely carries that.

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