architect_candidate_review

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

With openWorldHint=true and readOnlyHint=false already declared, the description adds genuinely non-derivable context: live=true triggers configured paid calls drawn against a shared budget, and the tool 'never accepts' (i.e., it does not approve/merge the candidate). Cost and non-approval behavior are exactly the things an agent cannot infer from annotations or schema. It stops short of saying whether artifacts are written to disk.

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 tight sentences with the core action front-loaded and the cost/consent constraint second; nothing is wasted. It is telegraphic to the point of near under-specification, but every clause earns its place.

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 4-parameter, open-world, cost-incurring tool with no output schema, the definition leaves real gaps: no indication of what evidence the review returns, no explanation of 'force', and no stated prerequisite for obtaining a valid change_id. The 'never accepts' note is helpful but the picture is only partially 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 coverage is only 25% (only 'workspace' documented), so the description must carry weight. It meaningfully explains 'live=true' as consent for paid calls within a shared budget — real semantics beyond a bare boolean. But 'force' and 'change_id' are left entirely undefined in both schema and description, and 'force' in particular (overwrite? bypass cache?) is a risky unknown.

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?

States a specific verb ('Review') and resource ('an exact candidate') and enumerates what the review comprises: checks, semantic judge, and all-document language evidence. That is enough to distinguish it from architect_sdd_check or architect_language_review, though the siblings are never named and 'exact candidate' is jargon that requires the change_id parameter to decode.

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 only implied: the tool evaluates a single candidate across check/judge/language dimensions. There is no explicit statement of when to prefer this over architect_language_review or architect_sdd_check, and no stated preconditions (e.g., an existing change_id from architect_sdd_propose).

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