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

With no annotations provided, the description must carry the full burden, and it does disclose that the operation is read-only, that the probes are side-effect-free, and that serper and jev probes cost one call each. The important caveat that `balance: null` means NOT MEASURED rather than zero is stated emphatically, which prevents a costly misinterpretation. It stops short of stating the required permission level or whether results are cached.

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 dense but well structured: it states the purpose first, then the return shape, then the null-semantics warning, then the alternative and cost notes. The backticks and warning glyph aid scanning, though the single long sentence about return values could be split for faster comprehension.

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 probe aggregator with no output schema, the description explains the return shape (`verdict`, `coverage`, `balance {restant, unite, limite?}`) and the full set of verdict values. The only material gap is the undocumented `_org` parameter, which matters here because the tool is an admin tool that could be scoped to an organization.

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 `provider` parameter is already documented in the schema, and the description mostly repeats that documentation with the same example (`fullenrich`). At 50% schema coverage, the `_org` parameter is undocumented in both the schema and the description, and the description does nothing to compensate for that gap. The baseline score of 3 is appropriate because the description adds little 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 states a specific verb and resource: it runs each connector's own side-effect-free probe against every PLATFORM key, and returns a verdict, coverage and balance per key. The `[platform admin]` prefix and the scoping to instance-paid keys distinguish it clearly from siblings such as `oto_connector` or `oto_admin_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 clearly states that the tool reads the remaining balance for every platform key and notes that the optional `provider` parameter can narrow the scope to a single connector. It also routes the agent to `oto_admin_monitoring` for connectors that have no balance to report, which gives a concrete alternative. However, it does not state explicit prerequisites or exclusions, such as an admin role or the conditions under which not to run it.

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