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

Annotations are minimal (readOnlyHint=false, destructiveHint=false, openWorldHint=false). The description adds valuable behavioral context: 'fully server-side (Floot mints all secrets; no keys to paste)', 'seeds the working code', idempotency ('re-running returns the existing resource and skips seed files that already exist'), and auto-provisioning for auth. It does not contradict annotations. A score of 4 because it covers the key side effects but could be more explicit about file modifications.

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 long (~200 words) but well-structured: main purpose first, then a bulleted list of resources, followed by exclusions and behavior notes. Each sentence carries essential information (idempotency, exclusions, beta-gating). It is not overly verbose relative to the complexity, though it could be tightened by trimming redundant phrases.

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?

Given the tool's complexity (7 resource types, exclusions, idempotency), the description covers all key aspects: what each resource does, exclusions, idempotency, and beta-gating. It lacks an explicit return-value description, but the mention of 'returns the existing resource' gives a hint. Overall it is sufficiently complete for an agent to invoke it correctly.

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 0%, so the description must compensate. It thoroughly explains each enum value of 'resource' with details on secrets injected, pages/endpoints seeded, and helper functions. For 'projectId', it is a standard identifier and not elaborated, but that is acceptable. The resource parameter semantics are far beyond the bare enum names, justifying a 4.

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 ('Provision a Floot-managed backend resource') and immediately clarifies scope ('for the project'). It lists the concrete resource types and distinguishes itself from siblings by naming request_external_resource and get_guides as alternatives. An agent can tell exactly what this tool does and what it does not.

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?

Explicit guidance is given for when to use this tool vs alternatives: 'SENDING email ... is NOT a resource' and 'For a user's OWN external key ... use request_external_resource instead.' It also clarifies that email is handled by get_guides("email"). This eliminates ambiguity and routes the agent correctly.

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