pi

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

With no annotations provided, the description carries the full behavioral burden, and it does substantial work: it discloses that pi blocks until completion, returns only final answer plus stats, has no permission system, edits files and runs shell commands as the user inside cwd, and that a timeout-killed run is resumable. A small gap is not describing the exact stats format or failure behavior, but the most important behavioral traits are covered.

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 compact yet dense: an opening behavioral summary, a clear 'Good for' section, and a Caution section. Every sentence earns its place. It front-loads the core behavior (starts a new task, blocks, returns session id) before routing and caution details, making it easy for an agent to parse 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 complex 9-parameter tool with no output schema and no annotations, the description provides a complete operating picture: session lifecycle (via pi_reply), model discovery (pi_models), steering/aborting (pi_send), timeout recovery, safety caveats, and parameter defaults. The combination of description and 100% schema coverage leaves little ambiguity about how to invoke the tool correctly.

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 100%, so the schema already documents all 9 parameters well. The description adds value beyond the schema by explaining which parameters to 'usually omit' (cwd, tools, transport, timeout_ms) and why, and by explaining the consequences of transport choices and timeout deadlines. This is helpful guidance an agent could not get from the schema alone.

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 states a specific verb ('Start a NEW task') and resource ('local pi agent'), and clearly distinguishes this tool from its siblings by explaining pi_reply continues sessions, pi_models lists models, and pi_send steers running turns. The scope is explicit: it blocks until pi settles and returns only the final answer plus stats prefixed with [session: <id>].

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 explicitly says when to use pi ('Good for: a second opinion from a different model, work kept out of this context, or parallel investigation') and offers clear caution about its lack of a permission system, advising to pass tools or no_tools for analysis-only work. It also references sibling tools for continued sessions and model listings, giving an agent actionable routing guidance.

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