todo_remove

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

Annotations already disclose the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), so the bar is lower, and the description still adds real value by disclosing the return value ('returns the updated list'), which lets a caller avoid a follow-up todo_list. It omits failure behavior for a missing id and does not explain why a removal is marked non-destructive. No contradiction: describing a scratchpad removal is consistent with destructiveHint=false.

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?

One short sentence, front-loaded with the action and scoped object, and it folds in the return value without any filler. Nothing would be gained by restructuring it.

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 one-parameter scratchpad mutation with a declared output schema, the description covers action, target, key, and return shape; the output schema relieves it of explaining response structure in detail. The remaining gap is error/edge-case behavior (unknown id, empty list) for a tool whose annotations say it is neither idempotent nor destructive.

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?

The single 'id' parameter has 0% schema description coverage, so the description must carry the load; 'by id' at least clarifies that the id identifies the todo being removed rather than a list or workspace. It gives no type, format, or origin guidance (e.g. that ids come from todo_list), so it only partially compensates.

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 a specific verb ('Remove'), a specific resource ('one todo from the scratchpad') and the keying ('by id'), which is unmistakably different from todo_add, todo_list and todo_update in the sibling set. It stops short of explicitly differentiating itself from todo_update, the other sibling that mutates a todo by id, so it lands at 4 rather than 5.

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?

Usage is only implied: the phrase 'by id' hints that an id from todo_list is required first, but the description never states when to remove versus update a todo, nor what to do when the id is unknown. No alternatives are named despite four todo_* siblings existing.

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