summarize_awards

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is covered. The description does add one genuinely non-obvious behavioral rule — prices are summed only for case numbers with exactly one source row and a usable price — which tells the agent results are filtered/deduplicated and may undercount. However, it leaves other behavioral questions open (what happens with duplicate source rows, whether results are comparable when a year lacks data).

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 short sentences, front-loaded with the core comparison purpose, with the data-quality caveat second. No filler or redundant restatement of the name.

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 annotations cover safety. Still, for a three-parameter tool with 0% schema description coverage, the unexplained query parameter and the undefined notion of a "usable price" leave gaps an agent cannot resolve from structured data alone.

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 0%, so the description has to carry the load; it clarifies fiscal_years (up to three distinct years) and implies ministry_code scoping, but the query parameter is never mentioned and ministry_code's format/role is not explained. This is helpful partial compensation, not full coverage.

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?

"Compare annual award snapshots by ministry for up to three distinct fiscal years" gives a specific verb (compare), resource (annual award snapshots), grouping dimension (ministry) and scope (up to three fiscal years). It does not name or distinguish itself from the sibling search_awards, so an agent must infer that this aggregates rather than retrieves.

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 comparison framing implies a use case, but the description never states when to pick this over search_awards, nor any exclusions or prerequisites (e.g., that it only makes sense with two or more years). The agent is left to infer routing from the verb alone.

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