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

The description adds valuable behavioral context beyond the annotations: it discloses that the update re-runs validation checks (self-link, cross-project, ancestor/descendant, cycles) and explains the app_url deep link behavior. No contradiction with annotations.

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 concise sentences, each with distinct purpose: explaining the full-update requirement, the validation behavior, and the recommendation to use partial-update with app_url context. No redundancy or filler.

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 description covers all essential aspects: full update semantics, required fields, validation behavior, alternative tool, and a useful deep-link detail. Despite having nested objects and no output schema, the description is comprehensive enough for an agent to understand the tool's behavior and invocation requirements.

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?

The schema only lists company_id, project_id, and pk, but the description specifies the critical body fields: 'predecessor, successor, dependency_type and lag_days must all be supplied'. This fills the gap left by the schema, which has no coverage for these essential parameters.

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 clearly states 'Full update (PUT) of a task dependency', providing a specific verb and resource. It also distinguishes from the partial-update sibling by explicitly calling itself 'Full update' and referencing the alternative tool.

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 advises 'Prefer the partial-update tool for small edits', giving clear when-to-use and when-not-to-use guidance. Also mentions re-running propagation and validation, which implies this is for cases requiring full re-validation.

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