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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds two genuine behavioral facts beyond that — result ordering favors exact names/codes, and long digit strings are treated as a single decode target — though both are stated ambiguously enough to leave the agent guessing at actual behavior.

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 is a good size and the verb is front-loaded, but the second clause is syntactically tangled ("postalref models, exact names and codes first"), costing clarity rather than saving space.

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?

An output schema and full annotations carry much of the load, so return format and safety need not be described. Still, for a search tool sitting among five competing siblings, the description does not give the agent enough to route confidently.

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% and the schema's own example ("055, mailer id, ground advantage") explains the query parameter better than the description does. The description adds no syntax, format, or limit guidance, 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?

It states a verb ("Search") and the resources searched (codes, terms, specs, documents), so the general purpose is recoverable. But the phrasing "postalref models, exact names and codes first" is garbled and never cleanly distinguishes this tool from siblings like lookup, define, or search_documents.

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?

There is no explicit when-to-use guidance and no named alternative. The only routing signal is indirect — "a query of 20 or more digits comes back as one to decode" implies the decode sibling exists but never says to call it instead.

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