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

Annotations already declare a non-read-only, open-world, non-idempotent write, so the bar is lower. The description still adds meaningful disclosure beyond them: drafts are private, nothing becomes public without the provider, no agent id is retained unless earn: true is set with a key, and the earn path carries commission terms (25% for 12 months). This privacy and side-effect detail is genuinely useful and not derivable from 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 a single sprawling run-on with nested parentheticals and referral legalese ('one level, terms 6c'). The front-loaded 'Free, no key' is a reasonable hook, but the core action is not cleanly separated from the incentive-program clauses, and a reader must parse the whole block to extract the operation.

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?

There is no output schema and four parameters, so the description should carry more of the burden. It explains the downstream flow (drafts prepared, provider invited) but never states what the caller receives back, nor whether the url must be reachable/valid. Adequate for the interaction model, thin on the return side.

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 75%; url, earn and looked_for all carry schema descriptions, while 'note' has none. The description expands on earn's referral mechanics ('you become the provider's referrer... 25% of PazAIr's commission... terms 6c'), which is more concrete than the schema text, but it adds nothing for url, note, or looked_for. Baseline 3 is appropriate.

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 action is buried behind marketing framing ('Free, no key. Found what agents look for somewhere else?'), but the operative clause 'Name the service (an MCP server, an OpenAPI document or an x402 endpoint)' does convey that the agent submits a service URL. The tool name 'tip' alone is ambiguous, and no sibling is referenced to sharpen the distinction (e.g. import_service or create_listing). Purpose is recoverable but not stated crisply.

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 implies the trigger condition: tip a service that agents look for but exists elsewhere rather than here. It does not name an alternative tool or state when NOT to use this versus siblings like import_service, discover, or create_listing. Usage is inferable but never explicit.

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