research_guide

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

With no annotations, the description carries the full behavioral burden. "Read" implies non-mutating and "No additional step is required" implies idempotence, but it never explicitly states there are no side effects, no auth requirements, or what happens on repeated calls. The note that profile is "legacy" is a useful deprecation signal that goes beyond structured fields.

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?

Sentence count is reasonable, but the prose is run-on and loosely ordered: the stage list, language, profile deprecation, task contrast, and methods all interleave. "No additional step is required." is filler, and "available_methods lists choices" points to a tool not present among the named siblings, which adds noise.

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 no explanation, and the description does cover all four parameters at least implicitly. Still, for a tool with zero annotation coverage and zero schema descriptions, it should state explicitly whether the call is read-only and confirm the full set of legal stage values rather than embedding them in a slash-separated phrase.

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, and it largely does: it enumerates accepted language codes ('en', 'zh'/'zh-CN'), explains methods as named capabilities with examples, tells the caller to omit the legacy profile argument, and effectively lists the stage values. Only the stage parameter's meaning is conveyed indirectly rather than stated outright.

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 states a specific verb and resource ("Read ... methods") scoped to a stage, and later implicitly contrasts itself with research_status for existing tasks. The purpose is discernible but the phrase "Read brief/collect/analyze/draft/review/revise/final methods" is dense enough that an agent must parse a stage list to get at the actual action.

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?

It names the alternative for an existing task ("use research_status to preserve its recorded completion requirements") and gives conditional guidance for the optional parameter ("Omit methods to keep stage defaults"). It does not, however, say when this tool is preferable to research_start or research_check_updates beyond that single contrast.

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