pi_research

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

With no annotations, the description carries the full behavioral burden; it does deliver the key claim "strictly read-only", which substitutes for readOnlyHint. It says nothing about duration, cost, permissions, or what a research task actually touches, and the read-only claim sits uneasily next to a writable-looking cwd parameter without explanation.

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?

Two short sentences, front-loaded with the core action and followed by the return/handoff note; nothing is padded or repetitive. It is terse for a seven-parameter tool, though that shortfall is better charged to completeness than to verbosity.

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?

A seven-parameter, annotation-free tool with no output schema and no parameter documentation needs considerably more than two sentences. An agent still cannot tell how to fill task vs question or which of host/model/endpoint matter, so the definition is not sufficient to invoke the tool confidently.

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?

Seven parameters with 0% schema description coverage, and the description names none of them. The overlap between task and question, the meaning of cwd/host/endpoint, and the effect of thinking are all left entirely unexplained, so the description adds nothing over an undocumented schema.

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 gives a specific verb and resource ("Launch a strictly read-only research task"), which is far more informative than the bare name pi_research. It also implies differentiation from pi_execute via "research" and "strictly read-only", though it never states that distinction explicitly.

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?

"Returns a job_id; wait for and inspect the result" implies a workflow that maps onto pi_wait and pi_result, but neither sibling is named and no condition for choosing them is given. Usage is inferable rather than stated.

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