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

The description goes beyond the annotations (readOnlyHint=false, idempotentHint=false, destructiveHint=false) by explaining concrete behaviors: the successor's planned dates are pushed forward, rejection causes are enumerated, and each dependency returns an app_url deep link. This provides valuable context about side effects and response details, with no contradiction to 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?

The description is four sentences, front-loaded with the main purpose, and every sentence adds essential information (behavior, constraints, return details). No fluff or repetition of schema data.

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 creation tool with no output schema, the description provides sufficient context: it explains the action, its side effect (pushing dates), error scenarios, and a key return field (app_url). Combined with the detailed input schema and annotations, it gives an agent everything needed to invoke the tool 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?

The schema only has a nested 'body' parameter with descriptions on its inner fields but no top-level description. The description compensates by explaining dependency_type values (FS/SS/FF/SF) and the meaning of lag_days (shifts constraint, can be negative), which adds semantic clarity beyond the raw schema. It does not repeat the existing descriptions for successor/predecessor IDs, keeping value high.

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 that the tool links two tasks of the same project with a scheduling dependency, using a specific verb (create/link) and resource (task dependencies). It distinguishes itself from sibling tools like destroy_taskdependencies and list_taskdependencies by focusing on creation and by detailing the dependency types and lag behavior.

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 specifies a key constraint: the two tasks must belong to the same project, and it lists rejection conditions (self-link, cross-project, ancestor/descendant, cycle) that guide when not to use this tool. However, it does not explicitly mention alternatives such as partial_update_taskdependencies for modifying existing dependencies, so it stops short of full when/why-not guidance.

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