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

Annotations only say non-readonly, non-destructive, non-idempotent. The description goes well beyond by disclosing the two validation gates, the override path, and a concrete Effects line. The refusal semantics are exactly the behavioral context annotations cannot convey.

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 the action, then rules, then effects — no filler. The long em-dash sentence and the opaque '(P-7)' policy reference absorb a little space that could have been trimmed.

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?

With no output schema, the 'Effects: receipt matched to transaction' line correctly covers the post-condition, and the validity rules are stated. It stops short of saying whether a match can later be undone or what is returned on refusal, but nothing critical to 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 the baseline would be 3; the description earns more by explaining what override actually overrides (total mismatch or >7-day date gap) and giving example reason content, which the schema's one-line 'Why this row' does not.

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 the exact verb and resource — 'Tie a receipt to one transaction' — plus the cardinality constraint (one receipt, one transaction). An agent can distinguish this from purch_unmatch_receipt and purch_link_refund without opening any schema.

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?

It spells out the preconditions for success (total must equal the row amount, dates within seven days) and the escape hatch (pass override with an explanatory reason, e.g. split payment or till tip). It does not explicitly name the alternative tools, but the when-to-use/when-refused boundary is unusually explicit.

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