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

With no annotations, the description carries the full burden and does add real behavioral context: a 100-item cap, recency bias, private/account-scoped visibility, an API key requirement, and a prompt-injection warning that returned evidence is untrusted data. It stops short of explaining ordering, pagination/truncation behavior, or what happens beyond the 100-item window.

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?

Three short sentences with the scope and limit front-loaded, followed by security and auth notes. Every sentence carries distinct information and there is no filler.

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 zero-parameter read tool with no output schema and no annotations, the description covers scope, volume limit, auth, and trust model, which is most of what an agent needs. The remaining gap is return shape and truncation/pagination behavior, which are not covered by any structured field.

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?

The tool takes zero parameters, so there is nothing the description needs to disambiguate at the argument level. Baseline applies; the description correctly implies no filtering inputs are available.

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 gives a specific verb ('Read') and a well-scoped resource ('recent private work opportunities owned by your account'), including a hard cap of 100. It doesn't explicitly differentiate itself from adjacent siblings like list_recurring_work, list_my_bounties, or record_work_opportunity, so sibling disambiguation is left to the 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?

Usage is only implied through scope: the data is 'owned by your account' and limited to recent items, suggesting a personal review use case. There is no explicit when-to-use, when-not-to-use, or named alternative among the many list_* / get_* siblings.

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