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

Annotations cover openWorldHint and destructiveHint, but the description adds behavioral context: 'Read-only — creates nothing' clarifies persistence semantics that readOnlyHint alone might not convey, and it discloses the return payload (ICP fields plus a draft sequence). It stops short of stating latency or cost, which is fine given the annotation baseline is met.

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, front-loaded with the input and output, then a behavioral note and a routing pointer. Every sentence carries information an agent needs; nothing is repetitive with the title.

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 2-param planning tool with annotations covering safety and no output schema, the description specifies the input, the produced artifacts, and the downstream handoff. What's missing is whether the output is persisted or ephemeral and whether re-running overwrites anything, but overall an agent has enough to invoke it correctly.

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 both 'website' and 'context' are documented in the schema with examples. The description adds no syntax or format details beyond the schema. Baseline 3 is appropriate when the schema does the heavy lifting.

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+resource ('builds an ideal-customer-profile and a suggested cold-email sequence') with the input that drives it ('given a company website'). It names the sibling consumers ('pass to copilot_launch'), so it is distinguishable from create_icp, plan_autopilot, and copilot_launch despite those siblings' similar names.

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?

Implies when to use it — planning before launch — and names copilot_launch as the downstream step, giving context. It doesn't explicitly state exclusions (e.g., 'use create_icp instead if you want a persisted ICP'), but the planning-to-launch flow is clear.

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