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

Annotations already convey readOnlyHint=true and idempotentHint=true, so the agent knows this is safe. The description adds behavioral context by specifying that it returns a paginated breakdown, includes DEF codes for disaster/emergency funding, and provides example codes/slugs. It does not contradict annotations and adds helpful detail about the data scope without over-explaining.

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 two sentences but packs substantial detail: the first sentence lists the core data returned, the second explains the identifier options and sources. It is front-loaded with the main purpose and uses examples efficiently. It is appropriately sized for a moderately complex tool, though it could be slightly trimmed without loss.

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?

Given that an output schema exists, return values are already specified, so the description need not restate them. It covers how to obtain the identifiers (from usaspending_list_agencies or award results), the mutual exclusivity rule, and the pagination behavior via sub_agency_page_metadata. The description is sufficient for an agent to call this tool correctly without additional introspection.

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% (every parameter has a description), but the tool description adds crucial semantics beyond the schema: it explains that toptier_code and agency_slug are mutually exclusive alternatives and provides concrete examples (097, 012; department-of-defense). It also clarifies that the page parameter is for sub-agency pagination. This extra guidance helps the agent select and format parameters correctly.

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 uses a specific verb ('Fetch') and a precise resource ('an agency's fiscal-year overview') and enumerates the returned data (mission, budgetary resources, obligation/outlay totals, DEF codes, sub-agency breakdown). It clearly differentiates itself from sibling tools like usaspending_list_agencies, which lists agencies, while this fetches details for one agency.

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 states that it accepts either toptier_code or agency_slug and explicitly says 'both appear in usaspending_list_agencies results and award search results,' guiding the agent on where to obtain inputs. It also instructs 'Use either toptier_code or agency_slug, not both,' which is a clear constraint. However, it does not explicitly describe scenarios where a sibling tool (e.g., usaspending_get_federal_account) would be more appropriate, but the purpose is clear enough that this is minimal.

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