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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), the description discloses important side effects and constraints: it returns an embed and a frozen styling contract that must be styled, requires owner approval, is unavailable until assignment, and is idempotent when retrying the same name while unassigned. This is exactly the kind of behavioral context an agent needs and that annotations cannot express.

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?

Every sentence carries operational weight: deployment timing, return value, styling mandate, approval prerequisite, dependency, retry behavior, naming convention, and services guidance. Critical constraints are front-loaded, and there is no filler or redundant repetition of schema details.

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?

The tool has nested parameters, no output schema, and multiple operational dependencies. The description compensates by specifying the return payload (embed + styling contract), the owner-approval requirement, the assign_to_project dependency, idempotent retry behavior, and the services-picker use case. For a complex create operation, the agent has enough context to call it correctly and know what to expect.

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. The description adds business-level meaning for key parameters: it mandates `services` for priced-service businesses, requires the currency, explains the auto-detected Data collection, and supplies a naming convention for `name`. This goes beyond the schema's field-level descriptions, though the schema still carries most of the detailed parameter documentation.

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 action and resource: 'Create a booking page BEFORE deploying (Plus/Pro).' It further distinguishes the tool by describing its unique output—'two-line widget embed + the frozen .db-* styling contract'—and by warning against reimplementing booking logic. This is clearly a create operation, not a get/list/delete sibling.

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 explicit temporal and dependency guidance: 'BEFORE deploying (Plus/Pro)' and 'Unavailable until assign_to_project', so an agent knows the prerequisite step and the correct ordering. It also tells when to pass `services` based on business type and requires owner approval. However, it does not explicitly name an alternative tool for non-booking flows, so it lacks a fully explicit when-not-to-use statement.

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