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

Beyond the annotations (readOnlyHint=true, openWorldHint=false, destructiveHint=false), the description adds important behavioral guarantees: 'Makes zero provider calls and no writes; never requests credentials, identity documents, bank/card data, or acceptance of terms.' It also discloses idempotency ('safe to repeat'), canonicality ('reads current server state and does not manufacture company facts'), and the confirmation boundary, all without contradicting the annotations.

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 description is dense and front-loaded with the most important scoping information, and nearly every sentence carries operational value. It loses a point because it includes some boilerplate redundancy, such as 'plus every prerequisite stated above' and a generic confirmation boundary paragraph that could be trimmed without losing meaning.

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 tool with 10 parameters, a nested repository object, and no output schema, the description covers purpose, usage boundaries, prerequisites, behavior, and idempotency quite thoroughly. It is slightly incomplete on what the returned commercial facts look like structurally, though it does say the tool 'returns only the commercial facts that genuinely need founder input.'

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 very low at about 10%, so the description must compensate. It does add meaningful guidance for the repository object by requiring the agent to inspect 'framework, package manager, app/source root, and test/build commands' itself, and it explains companyId usage with 'pass an exact companyId from get_company_briefing.' However, some required commercial fields like businessModel, billingModel, customerType, and targetCountries are only implicitly covered by the overall classification purpose rather than explained directly.

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?

The description leads with a precise scope: 'LEGACY PADDLE SUBSCRIPTION MIGRATION ONLY' and then states the tool's function: 'classifies whether the older fixed-price SaaS subscription Paddle merchant-of-record path fits, and returns only the commercial facts that genuinely need founder input.' It also names the sibling alternative, get_payment_pipeline_status, making the purpose and differentiation explicit.

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?

The description gives an explicit when-to-use and when-not-to-use rule: use for legacy Paddle subscription migration, but for a new Corply-controlled portal call get_payment_pipeline_status instead. It also instructs the agent to inspect repository metadata itself rather than asking the founder, requires an exact companyId from get_company_briefing when multiple companies exist, and warns not to bypass unsupported business models.

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