project

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

Annotations only include openWorldHint: true, so the description carries the burden. It discloses critical behavioral details: the auto-spawned production env is never auto-deleted, delete returns a 409 with environment_uuids when environments remain (no force/cascade), and delete_preview lists blockers without deleting. For create, the response shape { project, environment, environments? } is given. These go beyond the annotations to inform the agent of side effects and safety.

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 fairly long but well-structured, grouping information by action. It uses parentheses and semicolons to pack details efficiently. However, it could be slightly more concise; for example, the list of actions could be more compact. Still, every sentence serves a purpose, and the density of information is justified by the tool's complexity (6 actions).

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?

Given the tool's complexity (6 actions), the presence of an output schema, and the detailed input schema with full parameter descriptions, the description is remarkably complete. It covers required parameters (initial_environment), identification methods (uuid vs name), destructive action requirements (confirm), error cases (422, ambiguous match, 409), and the response structure for create. No obvious gaps remain.

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 100%, but the description adds meaning beyond the schema. For example, it explains that 'initial_environment' is required with no default and that the agent must ask the user for production vs custom name per D-09/D-10. It clarifies that get/update/delete/delete_preview accept uuid XOR name, and that name multi-match leads to COOLIFY_AMBIGUOUS_MATCH. It also notes that delete requires confirm:true and that deleting a project with remaining environments returns COOLIFY_409. These enrich the parameter semantics.

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 'Project CRUD (list, get, create, update, delete, delete_preview) for Coolify organizational containers'. It specifies the verb (CRUD operations) and the resource (project). The list of actions distinguishes it from sibling tools like 'database', 'system', etc., which operate on different resources.

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 explicit guidance on when to use each action: create requires initial_environment (must ask user), get/update/delete/delete_preview accept uuid XOR name, delete requires confirm:true. It also warns about error conditions like COOLIFY_422, COOLIFY_AMBIGUOUS_MATCH, and COOLIFY_409, and states that delete_preview lists blockers without deleting. This makes it clear when to use this tool and what parameters are necessary.

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