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

Annotations only convey the mutate/non-idempotent/non-destructive profile; the description adds substantial context: org-admin confirmation is required, a read-only probe runs first and writes nothing on failure, and the registration produces a prometheus_metrics source inheriting GitOps, audit, drift detection and IaC export. It also states no credential is needed for an in-cluster endpoint. Strong behavioral disclosure, though it could clarify reversibility of the registration itself.

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?

Dense but front-loaded: the core action and the verbatim-copy constraint come first, then behavior, then the exception case. Every sentence carries operational information, though the length is at the upper bound and could be tightened.

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 mutation tool with no output schema and a multi-step flow, the description covers the confirmation gate, probe, side effects, credential guidance and edge cases (external store, render mismatch). Nothing an agent needs to call this correctly is missing.

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, but the description adds real meaning: provider and endpoint must be copied verbatim from the refusal, are re-derived server-side, and any mismatch causes refusal. It also frames when endpoint_is_operator_supplied should be true. This is meaningful beyond what the schema alone states.

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?

States a specific verb (propose connecting) and resource (Prometheus-compatible metrics source) and grounds it in an exact trigger ('the one a query_prometheus refusal named'). An agent can immediately distinguish this from connect_log_source or query_prometheus without opening the schema.

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?

Explicitly names the triggering condition (a query_prometheus refusal naming a derived candidate), an explicit exclusion ('Do not use this to repair a misconfigured existing source'), and the alternative path (re-propose with endpoint_is_operator_supplied=true for external stores or render mismatches). Covers when, when-not, and alternatives.

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