abs_me

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

Beyond the destructiveHint/openWorldHint annotations, the description discloses the auth mechanism (Authorization Bearer from ABS_API_TOKEN), the self-hosted-only constraint, the confirm/dry-run protocol, and that destructive or credential actions (delete, scan, purge, backup restore, API key, password, settings) emit an extra warning in the preview. The schema also confirms secrets are redacted in output. This is substantive context an agent cannot get from annotations alone.

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?

The opening sentences are well front-loaded with auth, scope, and the dry-run/confirm protocol, but roughly half the text is a flat enumeration of 23 action names that duplicates the input schema's enum verbatim. That list earns no new information and dilutes an otherwise tight description.

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-operation dispatch tool with 6 parameters, no output schema, and destructive annotations, the description covers auth, runtime gating, dry-run behavior, and discovery via 'help' — enough for correct invocation. It stops short of describing return payloads or confirming that 'help' output is the canonical per-action contract, which would fully close the loop.

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 the baseline is 3, but the description adds meaning beyond the schema: that 'target' is the help lookup key, that 'params' are Express path parameters, and that confirm must be the boolean true while false and the string 'true' are rejected. That said, it does not explain which path parameters each action requires or what goes in body vs. query, leaving per-action parameter binding to the help action.

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 states it exposes the 'me' toolset with 23 actions against a self-hosted Audiobookshelf instance, and enumerates every action, so an agent knows exactly what surface it covers. It does not explicitly contrast itself with siblings like abs_sessions or abs_items, which expose similar verbs on different resources, so an agent must infer that this one is scoped to the authenticated user.

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 concrete selection guidance: use action 'help' with a target to discover an action's parameters, and writes require confirm=true plus ABS_ALLOW_WRITES=true. Omitting confirm yields a dry-run preview, which is a clear when-not-to-execute rule. What is missing is explicit routing between this tool and the sibling tools that overlap in verbs (sessions, stats, items).

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