mark_all_todos_done

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

The description explicitly states 'It changes remote GitLab state' and requires 'the necessary project or group permission,' which are important behavioral facts beyond the annotation 'openWorldHint: true.' It also lists possible error types (validation, conflict, permission, rate-limit). However, it does not disclose what happens to already-done items, whether the operation is atomic, or any side effects. The mention of project_id/group_id that are not in the schema introduces confusion rather than clarity.

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 description is verbose and padded with generic phrases like 'choose a sibling tool when you need a different resource or lifecycle action' and 'retains to the schema.' The first sentence is focused, but the rest repeats boilerplate that could apply to any tool. The mention of parameters not in the schema adds unnecessary length. It would be more concise if it simply stated the action, the permission requirement, and the error behavior without the filler.

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 tool with no parameters and no output schema, the description covers the core action, the fact that it mutates state, permission needs, and error response types. However, it includes irrelevant references to `project_id` and `group_id` that are not in the schema, and it omits details like whether 'all pending' includes items across all projects or only those accessible to the user. The mention of pagination fields is also nonsensical given no input parameters. These gaps reduce completeness.

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 schema has zero parameters, so there is nothing to describe. However, the description references 'project_id' and 'group_id' that are not present in the schema, which is misleading. It also says 'use required identifiers and pagination fields exactly as documented' when no identifiers or pagination fields exist. This actively confuses the agent instead of adding value, so it falls well below the baseline for a zero-parameter tool.

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 opening sentence clearly states the action: 'Mark all pending GitLab to-do items as done for the current user.' This distinguishes from the sibling 'mark_todo_done' by using 'all pending' and covers the resource and scope. However, the purpose is slightly diluted by later generic boilerplate that doesn't add specificity, but the core purpose is unmistakable.

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?

The description provides only a generic directive to 'choose a sibling tool when you need a different resource or lifecycle action.' It does not mention the alternative 'mark_todo_done' for a single item, nor does it state when this tool should be preferred over that one. No specific triggers, prerequisites, or exclusions are given, so the guidance is essentially absent.

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