weeek_update_task

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It notably discloses that the description update requires a knowledge base session and drives a headless browser (taking a few seconds) since Weeek's REST API ignores it on update. This is valuable transparency about side effects and requirements beyond the schema, though it doesn't fully explain behavior for every field combination.

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 a single compact sentence that efficiently enumerates the updateable fields. It's front-loaded with the main purpose and wastes no words. Slightly more structure could delineate the three categories more clearly, but the current format is economical and readable.

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?

This is a complex tool with 12 parameters including nested objects and enums, no output schema, and no annotations. The description covers the primary scope (fields, custom fields, description) and compensates for the lack of annotations by revealing the headless-browser behavior for description updates. It could be more complete by noting reversibility or partial-update semantics, but it addresses the key complexities reasonably well for its complexity level.

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 75%, so most parameters already have descriptions in the schema (dates format, priority semantics, tags referencing weeek_manage_tags). The description adds context for custom_fields (keyed by name or id, clearing behavior) and description (Markdown, headless browser via weeek_kb_update). With moderate coverage and a nested custom_fields object, the description adds value but doesn't fully detail the nesting semantics beyond what the schema already conveys.

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 the tool updates a task's core fields (title, priority, type, dates, duration, tags), custom field values, and description. It uses a specific verb ('Update') with a concrete resource ('a task's fields') and enumerates exactly what can be changed, differentiating it from sibling update tools like weeek_complete_task or weeek_move_task.

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 when to use it (when updating task attributes, custom fields, or description), though it doesn't explicitly state when NOT to use it or mention alternatives for other task operations like moving, assignees, or watchers. The specific mention of alternatives isn't required here since siblings handle discrete operations, but explicit exclusions would improve the score.

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