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

Annotations already declare readOnly/openWorld/non-destructive, and the description adds genuinely non-derivable behavior: the upstream API returns HTTP 500 on an empty filter set and that failure is intercepted with a clear error. It also flags the cross-parameter constraint that program_numbers only makes sense with grant/loan/direct_payment/other award types. It does not mention pagination or result caps.

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-loads the one-line purpose, then breaks scope, geo_layer, and the filter requirement into short labeled blocks. The program_numbers note is the longest block but earns its place by pairing a CFDA example with the award_type restriction.

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?

An output schema exists so return values need not be described, and the safety profile comes from annotations. But for an 11-parameter tool with 0% schema documentation, the description leaves too many filters opaque — notably def_codes (with a get_def_codes_reference sibling that could have been named) and the date format for time_period_start/end.

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% across 11 parameters, so the description carries the burden and does explain scope, geo_layer, program_numbers (with a Medicaid/CFDA example) and an award_type coupling. However def_codes, psc_codes, naics_codes, funding_agency, awarding_agency, and the time_period_start/end format are entirely undocumented in both places. About a third of the surface is covered.

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-and-resource statement: a geographic breakdown of spending. Combined with the sibling list (spending_by_category, spending_over_time, spending_by_transaction), the geographic axis is clearly distinct. It never explicitly names a sibling it is not, so it stops short of a 5.

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?

Gives concrete selection guidance for two of the enum parameters ('recipient_location' vs 'place_of_performance', and the three geo_layer values) and states the hard precondition that at least one filter is required. It also routes the agent to autocomplete_cfda for program numbers. It does not say when to prefer this over spending_by_category or spending_by_transaction, so no exclusion guidance.

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