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

Annotations only declare readOnly=false, destructive=false, openWorld=false; the description goes well beyond by disclosing the return payload shape, the meaning of findings_error, terminal statuses, and the non-cancellation semantics of the wait. It also surfaces a costly side effect the annotations do not capture: credit consumption tied to the clarity focus, including the refusal case for clarity-only requests and the 'not started' degradation when combined with other focuses.

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 purpose and behavior, and nearly every sentence carries distinct information (statuses, credits, exclusions). The prose is telegraphic and slightly dense, compressing several distinct ideas into semicolon-joined clauses, but there is little true waste.

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?

With an output schema present, the description need not restate return fields, and it still explains the status lifecycle, error semantics, and credit failure modes. For a two-parameter async-start tool, an agent has everything needed to invoke it and to know what to do next.

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 baseline would be 3, but the description adds real meaning by unpacking the enum into human-readable focus labels and by tying the 'clarity' value to a credit charge and a possible refusal/partial-not-started outcome. It does not add anything for invention_id beyond noting the innovation must be registered.

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?

Names a specific verb and resource ('starts automated analysis of a registered innovation description') and enumerates the focus areas covered. It also explicitly distinguishes itself from adjacent capabilities (novelty assessment, patent search, FTO, attorney review, patent preparation) and points to get_task_status as the continuation path, so an agent can place it precisely among siblings.

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?

Gives explicit when-to-continue guidance ('queued or running tasks continue through get_task_status with the same task_id'), states which statuses are terminal, and notes that ending the wait does not cancel analysis. It also carves out when NOT to use it by listing the separate request types it does not handle.

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