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

There are no annotations at all, so the description carries the full burden of disclosing side effects and sensitivity. The description does disclose credential/result persistence in transcripts and the header-argument precedence/conflict refusal, which is genuinely useful security context. However, it never states what the tool actually returns, whether it mutates state, or what happens when the signature is wrong, leaving the mutation behavior and outcomes opaque. That is a significant gap for the sole source of behavioral disclosure.

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 relatively short and each sentence carries information, but it's disorganized: the core purpose is one line, then a sudden jump to the terms, then auth configuration, then transcript persistence. The auth setup is arguably better placed in the MCP client config than the tool description. It is efficient but not well-prioritized.

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?

Given there is no output schema, no annotations, and only two required params, the description should explain return values, required auth flow for header vs pass, and what 'invoice/claim/recovery results' are. It does cover auth and sensitivity, but the absence of any output/return info and the undefined 'watcher' term leave a tool that has a credential-signing flow under-specified. It is adequate but leaves the agent with real gaps about side effects and return values.

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 0%, so the description must clarify the parameters. The description only explains 'pass' (a sensitivity fallback) and does not clarify id, txHash, or signature beyond their names. That is essentially no added semantic meaning for the params the agent must fill in. The 'pass' clarification is useful, but with 0% coverage and a required id/txHash pair, the agent is left guessing about formats: is txHash a hex string, what is id signing?

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's opening line states a specific verb and resources: attach a transaction to an invoice the watcher has not matched. However, 'watcher' is undefined context and the description immediately shifts into authentication details, dimming the core purpose. It remains distinguishable from siblings (mint_invoice) but only marginally, because the phrase 'attach a transaction to an invoice' is the only purpose statement and 'watcher' is jargon.

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 is explicit about when to use this tool: when the watcher has not matched a transaction to an invoice on its own. It also directs the agent to the terms (payment.sentADifferentAmount) for when a signature is required and what to sign. Though it doesn't name a sibling tool to prefer instead, it clearly scopes the use case and points to authoritative documentation. This level of usage guidance is strong.

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