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

Annotations already declare readOnly, idempotent, open-world and non-destructive, so the safety profile is free. The description adds real value by defining the match category semantics (A = exact, B = minor fix, C = uncertain) and stating that a best match plus address id come back, which tells the agent how to interpret partial matches. It omits what happens on no-match or whether the address is mutated in any store.

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?

Two sentences, front-loaded with the operation and immediately followed by the return shape. Nothing is redundant and no sentence could be cut without losing content.

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 single-parameter read tool with full annotation and output-schema coverage, the description supplies the one genuinely non-obvious thing: what the category codes mean. The only gap is the no-match behavior, which the output schema may cover.

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?

Only one parameter with 100% schema coverage, and the description's "messy free-text address" merely echoes the schema's "Address as typed by a person, with typos or missing parts." No formatting constraints, length limits, or examples are added beyond the schema, so 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?

Names a specific verb and resource ("Match a messy free-text address to the official one") and identifies the backing service (datavask), so the agent knows exactly what operation runs. It does not differentiate itself from plausible siblings like search_address or address_report, leaving the agent to infer the boundary.

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?

Usage is only implied: the phrase "messy free-text address" and the schema's "with typos or missing parts" signal this is for dirty input rather than already-normalized addresses. There is no explicit when-to-use, when-not-to-use, or named alternative, so an agent comparing it against search_address gets no routing guidance.

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