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

Annotations already declare idempotentHint: true and destructiveHint: false, so the safety profile is covered. The description adds useful behavior beyond the annotations: “the current preview is always free” (cost expectation) and “explicitly marks unresolved project relevance, document, or award-history evidence” (output quality and limitation). This gives the agent a realistic expectation of the result without repeating the annotation facts.

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 brief sentences and approximately 50 words. The purpose is front-loaded in the first sentence, the behavioral additions (free preview, unresolved-evidence marking) come second, and the “do not use” exclusions are placed last. There is no wasted text; each sentence earns its place.

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?

The tool accepts a non‑empty nested organization object with several required and optional sub‑fields, yet the description does not fully explain those fields or the expected prep work (e.g., what a “non-personal organization profile” entails). The presence of an output schema softens the loss of return-value explanation, but more parameter‑level guidance is still needed, so this is a 3.

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?

The schema description coverage is 50% — only opportunity_id is described in the schema, while the deeply nested organization object (with fields such as entity_type, state, country, and can_meet_cost_share) has no field descriptions. The tool description adds only the high-level constraint “non-personal organization profile,” which helps but is insufficient to fully compensate for the missing documentation of the nested fields. Given partial mitigation, a 3 is appropriate.

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 names the core action (“sourced go/no-go pursuit screen”), the specific resource (a single U.S. federal grant), and the required inputs (a non-personal organization profile and the official opportunity record). It also distinguishes itself from the discovery‑oriented sibling search_federal_grants by stating “Do not use it for discovery only,” which is a clear differentiator.

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 provides explicit when-to-use guidance (“Use this when the user needs a sourced go/no‑go pursuit screen”) and clear when-not conditions (“Do not use it for discovery only, legal eligibility advice, award prediction, drafting, or submission”). While it does not name the sibling tools, the exclusions are specific and actionable, earning a 4 rather than a 5.

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