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

Annotations only give the generic safety profile (readOnly=false, idempotent=true, destructive=false, openWorld=true), and the description adds substantial context beyond that: idempotent behaviour is spelled out as returning the existing record without updating it, conflicts are explained, credit refusal and free-retrieval semantics are stated, and family grouping side effects are disclosed. It even pre-empts a common misread by clarifying that an incomplete receipt does not mean work is still running.

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?

The core purpose and the own/competitor distinction are front-loaded, which is good, but the remainder is a dense prose block of a dozen sentences mixing idempotency, receipt semantics, credit rules and conflict handling. All of it is useful, yet the lack of any structure (sentences or bullets grouping the receipt/credit/conflict behaviours) makes it slow to scan for the one detail an agent needs.

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 write tool with an output schema, the description covers the return contract well — imported, receipt.status values, receipt.warnings, and null receipt meaning — so it does not need to restate the schema. The remaining hole is competitorCompanyName semantics and whether it is conditionally required, which is the one thing an agent could get wrong at call time.

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 only 33%, so the description has to carry meaning. It does well on purpose (own vs competitor, and that it comes from user intent) and reinforces that publicationNumber must be complete, but competitorCompanyName is never mentioned at all — an agent gets no hint about when to supply it or how it interacts with purpose=competitor.

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?

"Imports one public patent publication into the connected organisation" names a specific verb and resource, and the own/competitor split separates it from search_public_patents (discovery) and refresh_patent_family (maintenance). An agent can place this tool among its siblings 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?

Explicit routing guidance: own vs competitor is defined by the customer's intent rather than search results; repeated requests are safe to retry; a timed-out request can be re-run to retrieve the saved outcome; and get_credits is named as the way to check whether a new import costs anything. It also states what the tool cannot do (change purpose, replace publication), which is when-not-to-use guidance in practice.

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