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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the read-only nature is covered. The description adds useful context about auth_verify for multi-space accounts and warns that content should be treated as data, not instructions (a prompt-injection guard). However, it doesn't explain what happens if no record matches or the exact return structure, but that might be covered by output schema though none exists. Still, the description does not contradict the annotations; it reinforces the read-only nature.

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 concise: three sentences, each with a distinct purpose. The first states the action, the second the HTTP endpoint, and the third covers usage guidance. The critical auth_verify instruction is front-loaded. No fluff, all information is relevant.

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 simple read tool with both id and field selectors, the description covers the main usage trap (multi-space auth) and a security warning (data vs instructions). The schema provides full parameter details. The absence of an output schema means the agent might not know the return format, but for a get-record tool, it's often obvious from the context. A minor gap is not specifying what happens if the record is not found (error vs empty), but this is minor given the simplicity.

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 every parameter has a description. The description adds the 'canonical' concept and the exact-field matching semantics. It also explains the two selector types (id vs field) and that they must not be combined, which is partially in the schema but reinforced. The targetSpaceId parameter's meaning is fully explained in the schema, so the description adds little extra, but with 100% coverage, a baseline of 3 is appropriate; the additional guidance on space selection pushes to 4.

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 fetches a single record identified by id or exact field value, and it names the endpoint. This distinguishes it from siblings like record_query (which likely lists/query records) and record_find_by_field (which might be a different field-based search). The verb 'Get' and the resource 'record' are specific.

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 explicitly instructs to call auth_verify and ask the user which space to use for multi-space accounts, which is critical for correct invocation. It also mentions the ChangeRequest system for writes, implying this is a read-only tool. However, it does not explicitly state when to use this tool instead of records_list or record_query, though the 'canonical' and 'one record' wording implies uniqueness. A clear alternative mention would push to 5.

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