timps_self_critic_agent

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

With no annotations, the description carries the full burden. It discloses the core behavior (scoring, identifying weaknesses, auto re-run) but omits potential side effects such as cost implications, risk of infinite loops if threshold never met, or state changes from re-running agents. It also does not mention defaults for threshold/max_retries, though these are in the schema.

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 sentences, front-loaded with the primary purpose, and no redundant content. Every word contributes to describing the tool's function and its strategic context.

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?

Describes the core loop but lacks details on output format, error handling, or what constitutes an 'improved prompt'. With no output schema and no annotations, it could be more explicit about termination conditions and edge cases, but it provides a minimally acceptable overview.

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 100% with clear field descriptions. The description references threshold and retries indirectly but does not add new semantics beyond the schema's own parameter docs. Baseline of 3 is appropriate as schema handles parameter meaning.

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?

Description clearly states the tool scores outputs on a 1-10 scale, identifies weaknesses, and re-runs the originating agent with an improved prompt until a threshold is met. This verb+resource specificity distinguishes it from sibling tools like timps_dispatch or timps_run_task by focusing on the feedback loop.

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?

Implies usage for quality assurance across the swarm ('closes the quality feedback loop'), but does not explicitly state when to use this over alternatives like timps_agent_composer or timps_prompt_engineer. No exclusions, prerequisites, or when-not-to-use guidance is provided.

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