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

Discloses a critical behavioral trait absent from the annotations: the tool is hard-refused to agents regardless of role, so calling it is guaranteed to fail. It also describes the effect ('reconciliation signed off and kept as it stood: the figures, the items and a hash') and the required precondition (the reconciliation must be explained to the cent). Annotations only say it is a non-read, non-destructive, non-idempotent mutation; the description adds the refusal semantics that actually govern invocation.

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 purpose and the human-only warning are front-loaded, which is the right priority ordering. However, the agent-refusal point is made twice ('refused to you whatever your role' and 'it is refused the sign-off whatever its role'), which is redundant in an otherwise tight passage.

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 an agent cannot invoke, the description supplies everything needed: what it does, why it is off-limits, who should perform it, and what the agent should do instead (prepare and show rec_reconciliation). No output schema is required because the call path is closed to agents.

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 all three parameters (account, through, reason) are already fully documented with examples. The description restates 'with a reason' and 'through a statement's last day' but adds no syntax or format detail beyond the schema, so the baseline 3 applies.

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 ('Sign off an account's reconciliation') plus the scope ('through a statement's last day, with a reason'), which an agent can immediately distinguish from the sibling read tools rec_reconciliation, rec_signoffs and rec_match. The purpose is unambiguous and no sibling overlap is left to inference.

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?

Explicitly states when NOT to use it ('this act is refused to you whatever your role'), names the correct alternative path ('Ask your human to do it', 'An agent prepares it ... and shows rec_reconciliation'), and describes the division of labour between agent and human. This is the strongest form of routing guidance.

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