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

Annotations already disclose mutation (readOnlyHint=false), non-destructive and open-world behavior, so the description only needs to add context. It does add that the details are sent 'for review' (i.e., asynchronous adjudication, not instant activation) and that the new verification state is returned, which is meaningful beyond the structured fields. It omits what happens on rejection or whether an existing verification is replaced.

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 goal, but the first two sentences are near-duplicates ('so the merchant can accept live payments' / 'so the account can take live payments'), wasting one of three sentences. The required-field and return-value sentences do earn their place.

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 an 18-parameter, no-output-schema tool, the definition covers the goal, the mandatory inputs, and the returned state, which is the core an agent needs. It is thin on the many optional parameters (category, delivery, volume, usageClaims) and on the post-submission flow, but the schema carries those fields adequately.

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 baseline is 3. The description goes beyond the schema by naming which fields are actually required (legalName, country, street, city, url, acceptDeclaration, plus conditional registrationNumber), which the JSON schema does not encode since its required list is empty — a genuinely additive correction. It adds no syntax or format nuance beyond that.

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 and resource (submit business verification) with a clear outcome (merchant can accept live payments) and enumerates the fields required. It does not, however, differentiate itself from the close siblings agenta_verify_resubmit or agenta_verify_declaration, so an agent must still infer which of the three to call.

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?

Usage is implied by the goal statement (get the account to live-payment status), and the required-field list tells the agent what a valid call needs. There is no guidance on when to use this versus resubmit/declaration, nor any prerequisite or exclusion (e.g., what to do if a verification already exists).

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