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

Annotations only tell the agent this is a non-read-only, non-destructive, non-idempotent call. The description goes well beyond that: it discloses the auth requirement (signed-in subscriber), the consent gate, the notification policy (email only on a passing, higher-ranked model), and data handling (job and example tasks kept encrypted, deletable any time). This is exactly the additive context annotations cannot carry, and nothing contradicts them.

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?

Purpose and consequence are front-loaded in the first sentence, with prerequisites and parameter guidance following in a logical order. The consent and encryption clauses are dense but each carries necessary information, though the final sentence packs several parameter rules into one long construction.

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 seven-parameter mutation tool with no output schema, the description covers auth, consent, side effects, retention, and which parameters pair together. It stops short of saying what comes back (a job identifier or confirmation) or what happens on a duplicate watch, which would close the remaining gap.

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 100%, so the baseline would be 3, but the description adds relational meaning the flat schema cannot: that test_session comes from a finished comparison and carries its tasks, making it an alternative to supplying tasks directly, and that the discover session plus the current model are expected together. The exact syntax of current_model or runs_per_month is left to 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 states a specific verb and resource (saves a finished job for XF Model Watch) plus the distinctive behavior that defines the feature: re-testing as new models arrive and emailing only when a model passes every must-have and outranks on the person's priorities. That is enough to separate it from siblings like pick, rank, and compare, which do not persist a job for ongoing monitoring.

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 gives clear preconditions (signed-in subscriber, explicitly asking the person first) and a hard rule tying consent=true to their agreement. It also says what to pass along (the discover session, and either test_session or the tasks, plus the current model), but it never names a sibling tool or states when this should be chosen over alternatives such as pick or field_results.

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