pangolin_targets

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

Annotations already flag destructive=true and readOnly=false, and the description goes beyond them with the write-gating mechanism (confirm:true plus the PANGOLIN_ALLOW_WRITES env flag) and the dry-run preview default when confirm is omitted. It still does not say what a delete removes downstream (targets likely detach from sites/resources) or what the response looks like.

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?

It is front-loaded: identity first, then auth/write constraints, then a compact action list. Every clause carries information, though the three action lines are terse to the point of restating the operation names ('Delete a target', 'Get a target', 'Update a target').

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?

There is no output schema, and the description says nothing about return shape or the fields the body should contain when calling update_target, which matters for a tool with a free-form nested body object. For a three-action dispatcher that mixes reads and destructive writes, auth and confirm gating are well covered but the per-action payload contract is not.

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 carries most of the meaning, and the confirm explanation in the description largely restates the schema's own confirm text. The action-to-endpoint mapping does add a little by showing that {targetId} is a path parameter for every action, but it never names which key goes in the generic 'params' or 'body' objects for each operation.

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 ('the targets toolset') and enumerates all three operations with their HTTP verb and path (delete_target: DELETE /target/{targetId}, get_target: GET /target/{targetId}, update_target: POST /target/{targetId}). That is enough for an agent to separate it from siblings like pangolin_resources or pangolin_users, though it never states a plain one-line purpose such as 'manage Pangolin resource targets'.

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 preconditions: 'Self-hosted Pangolin CE only', 'Auth header Authorization Bearer', and 'Writes need confirm:true and PANGOLIN_ALLOW_WRITES=true', plus 'Omit confirm for a dry-run preview'. What it does not supply is when-to-use guidance between the actions (e.g., call get_target before update_target) or any routing note versus the sibling toolsets.

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