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

Annotations already cover read-only, idempotent, non-destructive and closed-world, so the bar is lower. The description still adds real behavioral context the annotations cannot: offers may overlap across providers, totals and stacking are not guaranteed, and the result is provisional until eligibility is verified — all important for how an agent should report the output.

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 short sentences, front-loaded with what is produced, followed by caveats and then the routing note. Slightly telegraphic ('Eligibility still needs checking.') but no wasted wording and no repetition of schema or annotation facts.

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?

Output schema exists, so return values need not be described, and annotations cover the safety profile. What remains is mostly the follow-up path after building a stack (verify eligibility, then claim), which is hinted at but not spelled out; otherwise the description is complete for a three-parameter read tool.

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%, so the description carries the burden. It does indicate that 'country' and 'audiences' are filters used to match offers, which adds meaning beyond bare field names, but it says nothing about the 'providers' parameter (accepted string format, whether names or IDs, limits) and nothing about country code format or the audience vocabulary.

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 output artifact ('build a candidate bundle across providers'), and the word 'candidate' plus 'eligibility still needs checking' makes clear this is a preliminary read, not a final claim. It doesn't explicitly contrast with close siblings like credits_for_stack or search_offers, but the 'candidate bundle' framing is distinctive enough to route an agent.

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 a concrete routing rule: if a provider is missing, use request_promotion, and explicitly states this read does not create requests. It also warns that eligibility requires a subsequent check. It stops short of naming which sibling performs that follow-up check (e.g. credits_for_stack / claim_offer), so one handoff is left implicit.

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