wallabag_annotations

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

Goes well beyond the annotations (destructiveHint=true, readOnlyHint=false): it discloses the OAuth2 auth source, the two-step confirm/dry-run write protocol, the WALLABAG_ALLOW_WRITES gate, and exactly which actions trigger an extra destructive warning (deletes, bulk URL lists, user registration). This is precisely the safety context an agent needs for a destructive tool.

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 and runs several distinct concerns (auth, environment, help, write gating, destructive warnings, action list) into a flat wall of sentences. Information is useful but not organized hierarchically, forcing the reader to parse it rather than scan.

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 multi-action aggregate tool with no output schema, it covers the important operational facts: auth, write safety, dry-run, help mechanism, and destructive-action set. The main gap is semantic -- it never says what an annotation is or what these operations return -- but the operational completeness is strong.

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 documents confirm, body, query, params, action, and target. The description mostly restates the confirm/target semantics already encoded in the schema (const true, help target), adding little beyond it. 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?

States the resource ('annotations toolset') and enumerates the four actions (delete/get/post/put_by_id), so an agent knows this is a Wallabag annotation CRUD surface. However, it never explains what a Wallabag annotation actually is (a highlight/comment on an entry), which is meaningful context for a domain-specific resource. Clear verb+resource, but no active sibling differentiation.

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?

Explains the mechanics well -- how to use action help, that writes require confirm=true and WALLABAG_ALLOW_WRITES, and that omitting confirm gives a dry-run. But it gives no guidance on when to reach for this tool versus the sibling wallabag_entries or wallabag_search, leaving routing to inference.

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