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

Annotations only give readOnlyHint=false, openWorldHint=true, destructiveHint=false. The description adds meaningful behavior: the model may return 'no-selection when nothing clearly matches', that it 'rank(s) existing variants', and the cost '2 MESH/call'. It does not clarify side effects beyond cost, but adds useful non-obvious traits.

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?

The description is a compact 50-word paragraph that front-loads the core action, then adds behavior, a boundary, and cost. Every sentence adds new information, with no fluff or repetition of the title.

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?

No output schema exists, so the description should convey return semantics; it says a 'best fit or no-selection' is possible but not what that looks like structurally. The tool is simple, but an explicit output shape would make it fully complete. Adequate for most calls.

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%, so the baseline is 3. The description reinforces the three inputs by naming them and gives examples for goal ('maximize trial signup') and profile shape, which adds a small semantic layer but is not essential beyond the schema.

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 opens with 'Choose which concrete content option to show a specific user and how to frame it' – a precise verb-resource-target combination. It explicitly limits the scope to 'rank existing variants' and adds 'not to invent a whole campaign from scratch', which distinguishes it from creative-generation siblings. This is unambiguous.

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?

It states when to use: selecting a content option for a specific user based on profile and goal. It provides an explicit exclusion: 'not to invent a whole campaign from scratch'. However, no sibling tool is named as the alternative, so it does not fully meet the 'explicit alternatives' bar.

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