oraclaw-mcp-server

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

Only provides efficiency comparison (10-100x); fails to disclose algorithmic traits (evolutionary/stochastic nature, black-box requirements, convergence behavior) despite no annotations.

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?

Extremely concise with three information-dense sentences; no filler content and immediately front-loaded with the algorithm identity.

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?

Critical gaps remain: no output schema is present and description fails to specify what the tool returns (optimal parameters, fitness value, covariance matrix?), nor does it address sibling tool differentiation.

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?

With 100% schema description coverage, baseline is met, but description adds no contextual meaning beyond schema (e.g., explaining objectiveWeights multi-objective implications or initialSigma's role in step-size adaptation).

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?

Clearly identifies CMA-ES for continuous optimization and parameter tuning, though it doesn't differentiate from sibling optimization tools (optimize_bandit, optimize_contextual).

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 via 'Tune parameters, calibrate models' and grid search comparison, but lacks explicit when-not-to-use or guidance versus alternative optimization methods.

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