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

Annotations declare readOnlyHint=true, idempotentHint=true, destructiveHint=false – the description aligns, stating computation (no mutation). It adds context that the tool handles both single vectors and matrices, and returns per-vector plus matrix-level stats. No contradiction. With annotations already covering safety, the description adds meaningful behavioral context about the data structure handling.

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, no wasted words. Front-loaded with verb and resource, then outcomes, then use cases. Every sentence adds value.

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?

Given the full schema coverage, clear annotations, and presence of an output schema (which presumably describes return format), the description is complete. It explains what the tool does, what data structures it accepts (vector or matrix), what statistics are computed, and when to use it. No gaps remain.

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% and each parameter has a clear description. The description adds value beyond the schema by listing computed statistics (not in schema) and clarifying that matrix overrides vector. The top_k default (5) is mentioned in schema but the description reaffirms it. Slight extra context about what statistics are returned improves usability.

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 ('Compute') and resource ('float vector or matrix of vectors'), lists the computed statistics (mean, std, L2 norm, min, max, sparsity, top-K indices), and distinguishes itself from sibling tools like normalize_vector (which normalizes but does not compute stats) and vector_similarity (which computes similarity). The purpose is clear and distinct.

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?

The description provides explicit use cases: 'debugging embedding quality' and 'analyzing vector distributions in a vector DB'. It implicitly distinguishes from siblings like vector_quantize, normalize_vector, and vector_similarity by focusing on statistics computation. However, it lacks explicit when-not-to-use guidance or alternatives.

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