Manage Projects

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

Annotations already declare destructiveHint=true, openWorldHint=true, readOnlyHint=false, and idempotentHint=false, covering the safety profile. The description adds scope (readme, fields, views, items, templates, links) but doesn't disclose what gets destroyed, permission requirements, or rate limits. A 3 is appropriate given the annotation coverage.

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?

Two sentences, front-loaded with the main purpose and operation categories. No wasted words, and the action-selection hint is appropriately placed at the end.

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 31 parameters, 38 action values, no output schema, and low schema coverage, the description is far too thin. It doesn't explain which parameters are required for which action or what the tool returns, leaving critical invocation details to inference.

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 13% across 31 parameters. The description only mentions the action field and lists operation names, leaving most parameters (org, name, repo, fieldId, etc.) undocumented. This does little to compensate for the low coverage.

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 'Manage GitHub Projects (v2)' and enumerates operations including create, list, get, update, delete, readme, fields, views, items, templates, and repo/team links. This is a specific verb and resource that distinguishes it from issue/PR management siblings, though it doesn't explicitly route against them.

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?

No when-to-use guidance is provided. The only directive is 'Use the action field to select the operation,' which is mechanical rather than a usage guideline. It doesn't explain when to choose this over manage_issues or other project-related tools.

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