Create task

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

With no annotations, the description carries the full disclosure burden for a write tool. It usefully reveals a side effect — resolving `cwd` can create a project — and a data-freshness behavior via file hashing. However it omits any permission/auth expectations, and it references `repo_root`/`repo_url`, which do not exist in this tool's schema, creating behavioral confusion rather than clarity.

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 sentences, front-loaded with the purpose and then the project-resolution rule; nothing is padded. The third sentence's reference to non-existent parameters spends space on unusable information, which keeps it from a 5.

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 an 8-parameter mutation tool with no annotations and no output schema, the description covers the trickiest part (project resolution and the `cwd`/`project` interaction) but says nothing about status, priority, files, or model behavior — it relies on the schema for those. The dangling `repo_root`/`repo_url` requirement is an unresolved gap an agent may try to satisfy and fail.

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 75%, so most parameters (priority, files, model, status) are already documented in the schema; description only adds guidance for `cwd`, `project`, and `body`, restating what the schema largely says. Worse, it claims registering a new project 'needs repo_root or repo_url too', but neither parameter is in the schema, so this instruction cannot be acted on. Baseline 3 with a mild accuracy penalty already absorbed by the misdirection.

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 opening sentence states a specific action and scope: capture work that will not finish this session. That framing distinguishes it from session-scoped siblings like log_entry, and the rest of the description covers project resolution. It never states plainly 'creates a task record', but the name/title plus the scoping sentence make the purpose unambiguous.

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 a clear usage condition ('work that will not finish this session') and routing rules between `cwd` and `project` for how the project is chosen. It stops short of naming exclusions or alternatives (e.g., use log_entry for work completed now, update_task to modify an existing task), so the agent must infer the boundaries.

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