abs_collections

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

Goes well beyond the annotations by naming the credential source (Authorization Bearer from ABS_API_TOKEN), the second env gate ABS_ALLOW_WRITES, and the fact that omitting confirm sends nothing at all — a genuinely non-obvious safety behavior. It also flags which action classes (delete, scan, match, purge, backup restore, user, API key, password, settings) emit an extra warning in the preview, which is real predictive context the annotations do not carry.

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-loads scope, then auth, then the confirm/dry-run contract, then the action list — a sensible order with almost no filler. The two long enumerations (nine actions and ten warned action classes) are dense and slightly run-on but each item carries distinct information.

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 six-parameter multi-action dispatcher with no output schema, this covers auth, environment gating, dry-run semantics, destructive-action warnings, the action inventory, and the self-documenting help path. What it omits — the individual action contracts — is intentionally delegated to 'action help with target', which is a reasonable design rather than a 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 coverage is 100%, so baseline is 3; the description adds workflow meaning by pairing confirm with the dry-run/execute distinction and pairing target with the help action. The ABS_ALLOW_WRITES dependency for writes is parameter-relevant context absent from the schema, though the confirm behavior itself is largely restated from the schema.

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?

Declares itself as the collections toolset for Audiobookshelf and lists all nine operations, which lets an agent separate it from abs_authors, abs_libraries, abs_items and the other siblings. The operation names (get, post, patch_by_id) are generic REST verbs rather than descriptive of what they do to a collection, so the resource scope is clear but the per-action semantics are not.

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?

Gives concrete routing rules: 'action help with target returns one action's parameters', 'Omit confirm for a dry-run preview', and writes require both confirm=true and ABS_ALLOW_WRITES=true. It excludes unsupported deployments ('Self-hosted Audiobookshelf only') but never contrasts with sibling tools, so an agent still has to infer that collections are distinct from libraries or items.

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