inbox

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

Annotations already declare a safe read (readOnlyHint=true, openWorldHint=false), so the safety profile is covered. The description does contribute genuine behavioral context: results are de-duplicated findings consolidated across daily runs, which tells the agent the data is aggregated and non-redundant. It says nothing about result volume, ordering, or how the neutral 'size' parameter affects 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?

A single dense sentence with the key qualifier (pending decision) front-loaded and the provenance detail in parentheses; nothing is wasted. It reads as a noun phrase rather than an action statement, which costs a little immediacy but keeps it compact.

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 read-only retrieval tool with no output schema, the description carries the full burden of explaining what comes back, and it does not — the shape of a 'finding', its ordering, and the effect of 'size' are all unstated. An agent can infer the topic but not how to page, scope, or interpret the response.

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?

With schema coverage at 50%, the description should compensate for the undocumented parameter, but it mentions no parameters at all. 'env' is covered by the schema (enum 'demo' plus a pointer to list_environments), while 'size' is a bare integer with no meaning supplied in either the schema or the description — the agent cannot tell whether it is a page size, a cap on findings, or a window.

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 names a specific resource — recommendations awaiting a decision — and adds a defining qualifier (de-duplicated findings across daily runs), which is more than a restatement of the name 'inbox'. It does not, however, contrast itself with plausible siblings such as knowledge or propose_knowledge, so an agent must guess where this queue ends and the knowledge tools begin.

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?

There is no explicit when-to-use statement, no exclusions, and no named alternative. The phrase 'still waiting for a decision' only hints that this is a pending-items queue; it never tells the agent whether to call this before or instead of knowledge/get_report, nor what to do with the results.

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