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

The claim 'Performs no writes' directly contradicts readOnlyHint=false in the annotations — the mirror image of the create_record calibration example. It also implies repeatable, side-effect-free behavior that sits uneasily with idempotentHint=false. The rest of the description (reachability check, auth verification, catalog surfacing) is genuinely useful, but the contradiction rule requires score 1.

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?

Three sentences with no filler: function, use case plus verifications, and sibling differentiation. The core action is front-loaded in sentence one and every subsequent clause earns its place.

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 tool with two parameter modes, no output schema, and a vague return description ('tool catalog'), the definition is adequate but gappy: it doesn't say how to pick server_url+headers vs integration_slug, doesn't describe the response shape, and the no-writes claim conflicts with the annotations, leaving the safety profile ambiguous. The strong schema descriptions compensate partially but not fully.

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% with strong per-parameter text (especially team_id's API-key-vs-OAuth rule and integration_slug's server-side resolution), so the schema carries the load. The tool description adds only light context — headers as 'authentication headers' and the URL as the probe target — and never explains the two mutually exclusive invocation modes (server_url+headers vs integration_slug), which the agent must infer from the schema enum.

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 a specific verb-resource pair — 'Probe an MCP server URL and list the tools it exposes' — stating the exact action and outcome. It also names the sibling checkMcpOAuth and the OAuth-support angle that distinguishes it, so an agent can separate the tools without opening schemas.

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?

The description gives an explicit trigger condition: 'Useful as a dry-run before creating a connection,' and spells out what it verifies (reachability, auth headers, tool catalog). It also names the alternative path — the OAuth check endpoint — and what that one probes for, providing clear when/when-not guidance.

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