spec_compare

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly states that the LLM must score both specs on four axes, which is a key behavioral trait not evident from the schema alone. It also implies the output format (radar charts). It does not mention whether there are side effects or external calls, but for a comparison/visualization tool this appears sufficient.

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?

The description is concise and effective: three short sentences that state the primary function, the required action (LLM scoring), and example use cases. It is front-loaded with the core purpose and contains no redundant information or filler. Every sentence contributes.

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?

Despite having 17 parameters, the description only mentions the four scoring axes and the comparison aspect. It leaves out the 'weakest' and 'tip' parameters, which are part of the required schema and have vague descriptions ('Left spec weakest axis', 'Left spec tip'). Since there is no output schema and no annotations, the description should have at least touched on these additional fields to provide a complete picture of what inputs are expected and how they are used.

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?

All 17 parameters have schema descriptions (100% coverage), so the baseline is 3. The description adds value by explaining that the score parameters (completeness, clarity, constraints, specificity) are to be filled in by the LLM as its assessment of each spec, which clarifies the ownership of these inputs. This goes beyond the minimal schema text like 'Left spec clarity' and helps the agent understand how to populate them.

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 clearly and specifically states the tool's function: 'Side-by-side radar charts comparing two specs.' It also indicates the action required ('YOU (the LLM) score BOTH specs on 4 axes each'), which differentiates it from siblings like spec_score (singular scoring) and spec_visualize (visualization). The use cases 'before/after or good/bad examples' reinforce its comparative purpose.

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 clear context for when to use this tool: when comparing two specs, as implied by 'comparing two specs' and 'both specs'. It also gives illustrative use cases ('before/after or good/bad examples'). However, it does not explicitly mention alternatives or state when not to use it, such as recommending spec_score for single-spec evaluation.

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