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

Annotations only declare readOnlyHint=false and openWorldHint=true; the description goes far beyond by disclosing that the server rejects requests when consent flags are false, enumerating prohibited sensitive data (SSN/tax ID, bank/routing/IBAN, card numbers, passwords, ID documents), forbidding extra fields, and describing the degraded result when sending is not available. For an external-send tool that is not idempotent, this is exactly the operational context an agent needs and cannot infer.

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, then a numbered mandatory checklist, then the fallback — logical order with no filler. It is dense and runs as one paragraph, and the field enumeration partially overlaps the schema, but every sentence carries operational weight.

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?

The tool is a high-stakes external send with nine parameters and gated consent; the description covers the trigger conditions, the exact data boundary, the rejection behavior, and the fallback path, while an output schema exists so return values need not be explained. Nothing an agent must know before calling it correctly is missing.

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 is 3, and the description adds real meaning on top: it defines the gate semantics for consent and user_confirmed (true only after the merchant's explicit yes in chat), enumerates the exact collectible field set including the optional Telegram handle and current processor, and constrains what_happened to shutdown/hold/other. It does not restate per-field formats (lengths, email format, monthly_volume in merchant's words), but those are already in the schema.

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 — send the merchant's application request to the PayFresco team — and immediately scopes it with 'This is the only tool that sends data,' which separates it from the read-only siblings (application_readiness, check_eligibility, assess_payment_setup). An agent knows exactly what this tool does and that no sibling substitutes for the send action.

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 an explicit four-step precondition sequence (ask about contact, collect only listed fields, show every value verbatim, get explicit yes) plus the failure condition (server rejects without consent/user_confirmed) and a named alternative path when sending is unavailable (application link and Telegram bot). This is when-to-use, how-to-qualify, and fallback routing all in one place.

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