update_project

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

With annotations declaring readOnlyHint=false, idempotentHint=true, and destructiveHint=false, the description adds value by specifying the 'reversible open/closed state' qualifier, clarifying that the mutation is safe and non-destructive. It also discloses the 'cannot change visibility or delete' constraints, which is useful beyond the annotation coverage. It doesn't add auth/rate-limit context but the annotations cover the safety profile adequately.

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 compact sentences: one states the core function, the second states limitations. Every word earns its place with no filler. Could slightly improve by naming the specific parameters updated, but the current form is efficient and front-loaded.

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 moderately complex tool with 8 parameters and 13% schema coverage, the description should compensate more. It addresses the mutation type, reversibility, and explicit constraints. However, with no output schema and poor parameter documentation, some behavioral context (e.g., what happens on partial updates, whether unspecified fields are left untouched) would strengthen it. The exclusions help but the parameter ambiguity and no output schema create gaps.

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 only 13% (just owner and projectId documented), so the schema leaves 6 of 8 parameters undocumented. The description lists which attributes it updates (title, descriptions, open/closed state), which maps to title, shortDescription, readme, and closed parameters. However, it does not explain the account/owner distinction or what hostname does. The description partially compensates for the coverage gap but doesn't fully document all parameters.

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 a specific verb+resource ('Update a GitHub Projects v2 title, descriptions, or reversible open/closed state'). It differentiates itself from siblings by explicitly naming what it cannot do (change visibility or delete), and it scopes to projects which distinguishes from update_repository_description, update_issue, and update_pull_request siblings. It loses a point because it doesn't name the specific sibling for alternatives (e.g., create_project or set_project_item_field).

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 gives clear context on what resources this tool updates (title, descriptions, open/closed state) and explicitly states exclusions (cannot change visibility or delete). However, it does not provide explicit when-to-use guidance against actual siblings like set_project_item_field, create_project, or update_release. The guidance is implied rather than explicit about alternatives.

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