Get one record

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds real value beyond them: plan-gated kinds ((Pro)) and a disclosed behavior for options.direction on organization_relationships. Missing are failure behavior for a bad ID and any note about record-not-found.

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: the core operation is the first sentence, then the ID-sourcing detail follows as a scannable per-kind list. Dense but nearly every clause carries information. Slightly hurt by the compact run-on formatting where kind lists and options notes are jammed into single lines.

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 20-way polymorphic getter with a 0%-documented schema, it covers kind meaning, ID provenance, plan gating, and per-kind options; output schema exists so return shape needn't be explained. The remaining gap is edge-case behavior (invalid ID, missing record, whether omitted ids error).

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 0%, so the description carries the full burden and does: it defines id semantics per kind (notice_id, PIID, UEI of 12 chars, CAGE of 5, subaward_sam_report_id, wd_id, office_code, organization_id) and enumerates the valid keys inside options for each kind that uses them. This is exactly the compensation the schema lacks.

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?

Opens with a specific verb+resource: fetch a single record by ID, and immediately distinguishes itself from siblings by stating IDs come from search results or resolve. The per-kind list makes the resource scope concrete. It stops just short of 5 because the first line alone is generic and only the follow-on list reveals what 'record' means.

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?

Explicitly routes the agent: IDs for each kind come from search(...) or resolve(...), and each kind is mapped to its source call. It also flags which kinds require the Pro plan. It does not state the inverse case (e.g., use search instead when you have no ID / want multiple records), which keeps it from a 5.

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