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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds real behavioral context: a 10-id ceiling, that ordering is meaningful ('best first'), that ids from search_jobs/search_awards silently do not render, and that the user-visible card displays the rows so the reply should be a short summary. It stops short of saying what happens on a second call (replace vs. append) or on an invalid id.

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?

Four dense sentences, front-loaded with the sequencing rule, then the input contract, then the exclusions. No filler and no restatement of the tool 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?

For a single-parameter tool with an output schema, the description covers sequencing, valid id sources, the 10-item limit, ordering, and the expected assistant reply style. Nothing an agent needs to call it correctly is missing.

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% and the schema already documents order and maxItems, so baseline would be 3. The description goes further by constraining where valid ids may originate (search_contracts/search_grants results, not search_jobs/search_awards), which the schema's generic 'id field of a search result' does not convey.

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?

States a specific verb and resource ('show the user the opportunities you picked as a card') and immediately distinguishes itself from siblings by naming search_contracts, search_grants, and get_opportunity as the wrong tools. An agent can route to it 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?

Explicit sequencing ('Use this last, after searching'), an inclusion rule (ids from search_contracts or search_grants), an exclusion rule (ids from search_jobs or search_awards are not shown), and two named alternatives to avoid (search_* and get_opportunity). Nothing is left to inference.

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