ps_research_step

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

With no annotations, the description carries the full burden. It does disclose useful traits: one round per call, verb selection, the parking/pending_request behavior, and the delta-only return that keeps cost proportional to changes. It omits auth requirements, error handling, idempotency/re-entrancy semantics, and what happens if the session is already finalised.

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 core action and return shape are front-loaded in the first sentence, and the following sentences add the verb set and payload semantics without much waste. It is slightly dense with parenthetical asides but remains appropriately sized.

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?

An output schema exists, so return values need not be re-explained, and the description does convey the round/parking model. For a 4-parameter tool with zero schema description coverage and no annotations, however, the gaps in parameter meaning and usage routing leave it short of complete.

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 0%, so the description must compensate for all four params, yet it explains none of them. It implicitly references 'the message' (fold the message into the question tree) and mentions pending_request (which is not even a parameter), but session_id, config_path, and periscope_path are entirely undocumented.

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 and resource ('advance a research session by ONE round') and clarifies the scope is a single step returning a delta rather than a full tree. It is clear what the tool does, but it never explicitly names or contrasts the sibling tools (ps_research_followup, ps_research_answer, ps_research_draft) that an agent might confuse it with.

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 is implied by the loop semantics: the tool advances a round and may park with a non-null pending_request when input is needed. However, there is no explicit statement of when to call this versus followup/answer/status, nor any prerequisite guidance, leaving routing to inference.

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