add_project_item

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

Annotations only declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, which offer minimal behavioral info. The description adds the key constraint that only existing Issues/PRs can be added (not drafts), which is useful. But it doesn't disclose behaviors like whether duplicates are prevented, error conditions (e.g., item already in project), or required auth/permissions.

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, both meaningful and non-redundant. The first states the tool's function and the second states a key limitation. No wasted words or fluff. Slightly more structure could be added but the description is appropriately tight.

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 7 parameters and no output schema, the description is thin. It explains the primary operation and one limitation, but doesn't clarify parameter interactions (which fields identify the item vs. the project), error conditions, or behavior when the item already exists in the project. With no output schema to clarify returns and minimal annotation coverage, the description should carry more of the explanatory burden.

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 coverage is 14%, meaning most parameters are undocumented in the schema. However, the required fields (account, repository, owner, projectId, contentType, number) have fairly self-evident meanings from their names and patterns. The description clarifies contentType accepts only issue or pull_request. Still, it doesn't explain relationships between fields (e.g., why both account and owner are needed, or what the number refers to). With low schema coverage, more compensation would be expected.

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 it adds an existing Issue or Pull Request to a GitHub Projects v2 project, using specific verbs and resources. It distinguishes from siblings like set_project_item_field and list_project_items by focusing on adding items. However, it doesn't explicitly differentiate from update_project or create_project.

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 states 'Draft items cannot be created,' which is a clear exclusion/limitation. However, it doesn't provide explicit when-to-use guidance or name alternative tools for creating draft items or creating new projects. The context is implied by the tool's purpose rather than explicitly stated.

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