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

Annotations cover safety profile (not read-only, not destructive), and the description adds substantial behavioral context beyond them: report_instructions are 'scanned for secrets and prompt-injection phrasing before anything is saved,' the department is created as a personal DRAFT that is never published or reviewed, and it works only 'once its members are available.' This is exactly the kind of trait annotations cannot express.

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?

Front-loaded with the core definition and required params, then progressively adds pattern semantics, the report_instructions side effect, the draft-only nature, and membership constraints. Dense but every clause carries information; slightly long for a description but no filler.

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?

Even with a rich schema and output schema present (so return-value explanation may be abbreviated), the description covers creation semantics, validation constraints, security scanning of report_instructions, the draft lifecycle, and hard refusals of unsupported modes. An agent has everything needed to call this correctly and to know what it should not attempt.

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 100%, so the schema already documents all seven parameters including the hub/entry/alias/role defaults. The description adds marginal value by explaining pattern semantics ('pipeline members run in order', hub-orchestrator requires hub, p2p optionally entry) and the alias/role relationships, but largely reinforces existing schema text. Baseline 3 is appropriate.

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 (Create) and resource (department), immediately resolving the ambiguous term by defining it as 'a team of 2-16 EXISTING published agents with a topology.' This distinguishes it from sibling findagent_create_org (organization) and findagent_create_draft (single agent).

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?

Provides clear preconditions (each member must be a published public agent; an OAuth-signin agent cannot be a member yet) and explicitly routes unsupported configurability to the web builder ('refused here, not ignored'). No explicit when-not-to-use against edit_department or create_org, keeping it short of a 5.

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