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

Goes well beyond annotations (readOnlyHint=false, destructiveHint=false) by disclosing a side-effect (re-running successor scheduling propagation), specific failure modes (self-link/cross-project/hierarchy/cycle checks with 400), and a response feature (app_url deep link to the successor's drawer). This is rich, non-obvious behavior an agent needs, and it is consistent with the 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 tight, front-loaded sentences: action, side-effect, and constraints/response detail. No filler—each sentence earns its place and the structural flow from intent to consequence is ideal for an agent scanning quickly.

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 mutating tool with no output schema, the description covers the core scenario: fields, side-effect, error conditions, and a response attribute (app_url). Minor gaps include lack of detail on the exact response envelope or whether dates can also be pushed backward (only 'forward' is mentioned), but overall it is thorough for the tool's complexity.

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?

Although schema coverage is 0%, the description does name the two mutable payload fields (dependency_type, lag_days) which are absent from the top-level schema — genuinely useful. However, it does not clarify value formats or constraints (e.g., allowed enum for dependency_type, range for lag_days), and with zero schema-coverage in the description, it could have compensated more.

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?

Uses a specific verb ('Change') with a specific resource ('a dependency's dependency_type or lag_days'), and appends the HTTP method (PATCH). This distinguishes it from sibling tools like the full update_taskdependencies, making the scope (partial update of two fields) unmistakable.

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 implies this tool is for modifying dependency_type or lag_days, which signals selection over the full-update sibling, but there is no explicit when-to-use/exclusion statement or named alternative. Usage context is visible only through the narrow field list, leaving the agent to infer the comparison.

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