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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the mutation-without-destruction profile is conveyed structurally. The description adds value by disclosing that 'List also returns accessible workspaces,' a non-obvious behavioral trait, and the schema adds replace-semantics for tags ('Updating replaces the full list'). The description does not contradict the annotations.

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?

Three sentences, each with a distinct job: sentence one states the core purpose, sentence two gives the critical workflow constraint, sentence three discloses a non-obvious return value. There is zero filler or repetition of schema content, and the purpose is 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 12-parameter, three-action tool with no output schema, the definition is largely complete because the 100%-covered schema thoroughly documents action-scoped parameter applicability. The description covers the essential ordering constraint (list to obtain projectId for update and other tools) and the workspaces return. The only real gap is that neither the description nor an output schema hints at what create/update return, leaving the agent to infer that create yields a projectId.

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%, so the baseline of 3 applies and the description rightly leans on the schema for parameter meaning. The schema descriptions are genuinely rich — the action enum defaults to 'list', projectId is marked required for 'update', limit has defaults and max — so the tool's parameter semantics are fully conveyed without the description needing to repeat 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?

The description opens with 'List, create, or update AdKit projects' — a specific multi-verb statement tied to a named resource that instantly tells an agent what the tool does. It also distinguishes the tool from siblings by identifying it as the project entry point in the AdKit family, complementing rather than duplicating the purpose of adkit_studio, adkit_manage, or adkit_library.

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 second sentence, 'Use a projectId returned by list for update and other project-scoped tools,' establishes a clear list-first workflow and routes the agent from this tool to dependent project-scoped operations. It provides clear context for the primary usage pattern, though it stops short of naming specific alternatives or stating explicit when-not-to-use conditions.

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