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

Annotations provide readOnlyHint=true, so the description doesn't need to emphasize read-only. The description adds behavioral context: it mentions 'Free geography utility' (no payment), 'Public calls never expose WIP or relationship-only records' (privacy/filtering), and that read_wip is for operator review. This adds non-obvious details beyond the annotations, such as the concept of WIP records and the loopback-only restriction. However, it doesn't specify pagination or response structure, which could be useful but the annotation covers safety.

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 three sentences, information-dense, and front-loads the core purpose. It lists many specific data attributes (row counts, vintages, target levels) which adds length but is relevant. It could be slightly more concise by trimming some enumerations, but it remains efficient and readable.

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 the tool is a read-only listing/directory function with annotations covering safety, the description provides a complete picture: what it returns, what filters to use, what it excludes, and when to call it. There is no output schema, so the description must convey the return concept, which it does by listing the kinds of artifacts. The description covers the essential guidance an agent needs to invoke correctly.

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 100%, so each parameter is described in the schema. The description adds practical guidance: 'Pass country_scope whenever the country is known' and explains read_wip is for operator review. It doesn't heavily elaborate on parameters but provides context that helps the agent decide how to use them, such as country_scope for focused answers and include_crosswalks default. Since the schema already covers semantics, the extra guidance pushes it above baseline 3.

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 clearly states the tool reads a 'canonical crosswalk registry' and lists published, callable geographic reference systems, crosswalk artifacts, row counts, vintages, etc. It explicitly mentions the types of identifiers (ZIP/ZCTA, postal, census, etc.) and states its purpose: to learn whether identifiers can be exchanged through loc_id. This is specific and distinct from siblings like identify_reference_system or loc_id_info.

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 explicitly says 'Pass country_scope whenever the country is known' and 'Call this first to learn whether...' providing clear when-to-use guidance. It also notes public calls never expose WIP or relationship-only records, which implies usage restrictions. It does not name specific sibling alternatives but provides enough context to distinguish this as an initial discovery tool.

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