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

No annotations are supplied, so the description carries the full behavioral burden. 'Diagnostic gate only' usefully signals a non-mutating evaluation and 'no tax math' rules out calculation side effects, but it says nothing about permissions, persistence, or what a readiness verdict looks like.

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, no filler, with the two mandates front-loaded and the scope restriction second. Nothing needs to be re-read or hunted for.

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 seven-parameter, dual-mandate tool with no output schema and no annotations, the description covers the what and the boundary but not the how: it doesn't explain how inputs are consumed per mandate (especially the 'both' value) or what a readiness result consists of. Adequate, but an agent still has to infer part of the calling pattern.

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?

There is no scope note here to add, but the schema itself defines every parameter, including required 'mandate' (with enum), 'sprs_score', 'building_sqft', and the boolean flags, so the agent can populate them directly. My score reflects that completeness rather than any extra wording.

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 names a specific verb ('Check') plus two precisely-scoped regulatory regimes (IRS 179D / Form 7205 and DoD CMMC 2.0 / NIST SP 800-171 SPRS). That specificity is enough to separate it from siblings like check_cbp_drawback_eligibility or check_eu_cbam_eudr_mandate without opening any schema.

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?

'Diagnostic gate only; no tax math' establishes a clear usage boundary and tells the agent this is a pre-qualification screen, not a deduction calculator. It stops short of naming triggering conditions or an alternative tool for actual tax computation, so it falls short of a full when/when-not/alternatives treatment.

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