my_issues

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

The description explicitly states the tool is read-only and does not mutate GitLab data, aligning with the readOnlyHint annotation. It also details error scenarios (missing resources, invalid identifiers, insufficient permission, rate limits) that are not covered by the annotations alone. This adds valuable behavioral context for the agent.

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 wordy, with repetitive phrases like 'use this for the specific operation described' and 'use required identifiers and pagination fields exactly as documented.' It could be more concise while retaining essential information. The structure is linear but not particularly streamlined.

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?

While the description mentions read-only behavior and error types, it lacks information about the expected output format or structure, especially given there is no output schema. It also does not clarify pagination behavior beyond a vague reference. This leaves the agent with incomplete context for handling the response.

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 already provides full coverage and descriptions for all 11 parameters, so the description adds little beyond mentioning that project_id can be omitted to search across all accessible projects, which is already in the schema. The reference to 'group_id' in the description is not present in the schema, slightly reducing clarity. Since schema coverage is 100%, the baseline of 3 is appropriate.

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 clearly states the tool's purpose: listing issues assigned to the authenticated user. This distinguishes it from general issue-listing tools like 'list_issues' by focusing on the current user's assignments. The phrase 'the specific operation described' is somewhat redundant but does not obscure the core functionality.

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 advises to use this tool for the specified operation and to select a sibling tool for different resources or lifecycle actions. While this is explicit, it lacks concrete distinction from closely related tools like 'list_issues' or 'get_issue'. The guidance is somewhat generic and could benefit from specifying when 'my_issues' is preferred over alternatives.

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