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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds significant behavioral context beyond these: it documents that the tool never raises protocol errors on invalid input (returns an error object instead), describes the licensing restriction ('PREMIUM'), limits task scheduling to the first 30 tasks, and confirms idempotency explicitly. None of these details are present in the annotations, and there is no contradiction with the annotated hints.

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 well-organized and front-loaded with the core purpose and the critical licensing note. It then covers input/output example, usage guidance, error behavior, and safety. Every sentence serves a distinct purpose (scope, example, usage rules, error handling, idempotency). No redundant content is present. It could be slightly more concise (e.g., the error section is a bit long), but overall it is efficient and structured.

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 moderate complexity (4 parameters, output schema), the description covers all necessary aspects: the fundamental backward-scheduling logic, input/output structure (including an example), usage rules vs siblings, error response format (ensuring the agent knows how to interpret failures), idempotency and safety for retries, licensing restrictions, and the task limit. The presence of an output schema is noted, but the description still explains the returned fields meaningfully. Nothing critical 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 description coverage is 100%, so the baseline is 3. The description adds value by providing a concrete example of the tasks array structure and the expected output fields, which helps an agent understand parameter interplay. It also clarifies behavioral limits (first 30 tasks scheduled) and the purpose of buffer_days as a safety margin, which reinforces the schema. This extra context lifts the score above the baseline but does not reach a 5, as the schema already documents each parameter thoroughly.

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 precise verb-resource pair: 'plan a task schedule backward from a hard deadline in business days.' It immediately clarifies scope (backward scheduling from a fixed end date) and distinguishes itself from sibling tools by explicitly stating 'Not for forward counting from a start date (business_days) and not for response-time targets (sla_due).' The example input/output reinforces the tool's specific functionality, making it unmistakably distinct from related tools.

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 provides clear usage context: 'Use when the end date is fixed and steps must be placed backward from it. Not for forward counting from a start date (business_days) and not for response-time targets (sla_due).' It names the specific sibling alternatives and gives explicit when-to/when-not-to instructions. Additionally, it explains error handling behavior ('never raises a protocol error — it returns {"error": ...}') and retry safety ('it is always safe to retry'), which are actionable guidelines for the agent.

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