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

Annotations only carry destructiveHint=true, so the description adds real behavioral value: a WRITE marker and, more importantly, idempotency semantics ('if an active project with the same name exists, that project is returned') plus the standard defaults. It does not address auth/permission needs or whether an archived/non-active project causes a failure or a new project.

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?

Dense but front-loaded: the operation type, then the resource, then the idempotency rule, then defaults. The trailing 'Depot: ProjectService/CreateProject.' is internal jargon that adds little for an agent, but the rest earns its place.

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 an 8-parameter creation tool with no output schema, the description covers defaults and idempotency but omits what the caller receives back (project ID, fields) and any organization/permission prerequisites. Adequate but with clear gaps an agent would have to discover empirically.

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% and each parameter is documented with ranges and defaults, so the baseline is 3. The description restates the cache and hardware defaults already in the schema and adds no syntax, format, or interaction detail beyond them.

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 a specific verb and resource (create a Depot container-build project) and immediately defines what the resource is ('an isolated build cache'), which distinguishes it from depot_get_project and depot_list_projects. An agent can select it without opening the schema.

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?

Usage is implied rather than stated: idempotency by name signals this is safe to call when unsure whether a project exists. However, no sibling alternatives are named and there is no explicit when-not condition (e.g., use depot_get_project to look up an existing project first).

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