add_task

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

Annotations already cover safety (readOnlyHint=false, destructiveHint=false), and the description adds real behavior: new tasks always land in backlog, `text` must be a single line or it errors, `plan` is stored separately and visible via get_task, and `title` is what renders on kanban/calendar. It does not address duplicate handling or what the call returns, which is the remaining gap.

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?

Front-loads the required fields and the backlog default before per-parameter detail, so the most decision-relevant facts come first. There is minor redundancy (the title length constraint is restated as a rationale, and required-ness is emphasized twice), but nearly every sentence carries actionable information.

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 9-parameter creation tool with no output schema and no nested objects, the description covers validation constraints, defaults, field formats, and storage side effects well enough to call it correctly. The only omission is what the tool returns (e.g. the new task identifier) and any duplicate-prevention behavior implied by idempotentHint=false.

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?

With 0% schema description coverage across 9 parameters, the description carries the full load and does so: it marks text/title as required, gives `priority = asap|high|low`, `deadline = РРРР-ММ-ДД`, `energy = S|M|L`, separator conventions for domains/links, and a concrete example path for `links`. This supplies enum values the schema itself lacks, which is exactly the compensation needed.

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?

Opens with a concrete verb+resource ("Додати задачу" = add a task) and immediately qualifies the two mandatory fields, so the agent knows exactly what operation this is. It does not explicitly contrast itself with edit_task or the other siblings, but the creation semantics ("Нова задача завжди потрапляє в backlog") make the boundary inferable.

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?

Gives clear situational rules: always set `links` when the task grows out of a specific note, put multi-line descriptions in `plan` rather than `text`, and use `project` empty for the global scope. It stops short of naming alternatives (e.g. use edit_task to change an existing task), so it is strong context without explicit exclusions.

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