task_create

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

With no annotations, the description carries the full burden and does so well: it explains that a duplicate key returns the existing task unchanged with existing=true, that results can carry similarity warnings to check before continuing, and that human approval gates progression. It stops short of describing permissions, what a successful create returns beyond warnings, or failure modes.

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?

It is a single dense block built from field-to-meaning pairs, front-loaded with the verb, with no filler sentences. Each clause adds a rule or constraint rather than restating the schema.

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 15-parameter mutation tool with no annotations and no output schema, the description does the heavy lifting on idempotency, approval gating and the similarity warning, which is what an agent most needs. A couple of parameters and the shape of the created record remain unexplained.

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 coverage is 0%, so the description must compensate, and it explains key, source, status, due, done_means, ask, approved_by, approval_source, evidence and test_results with real meaning beyond type. Gaps remain: note and approval_needed are never defined directly, and approved_by versus approval_source is left ambiguous.

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?

"Create a task" gives a specific verb and resource, and the rest of the sentence enumerates what the created task carries. It never names siblings like task_update or task_import, so the agent must infer the create-vs-update boundary, but the intent is 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?

Usage rules are stated for parameters rather than for tool selection: key makes retries safe, ask is mandatory when status is waiting_on_owner, approved_by is mandatory before an approval_needed task can be in_progress or done. Nothing tells the agent when to reach for task_import or task_update instead, so selection guidance is only implied.

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