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

The description goes far beyond the annotations by revealing critical behavioral details: filters are case-insensitive substring matches; amount-remaining must be reported from leftGrams/totalGrams and percentLeft, not raw total/left which are internal length in mm; density is used for gram conversion and densityIsEstimated indicates a default density assumption. These insights are not available from annotations or the schema, adding substantial transparency. No contradiction with the readOnly/idempotent 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?

Every sentence earns its place. The description is dense but well-structured: purpose first, then usage patterns, then the get_filament fallback caveat, and finally the unit/conversion warnings. No filler or repetition of schema content. It packs maximum useful guidance into a compact block appropriate for a complex 10-parameter tool.

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 tool has 10 parameters and no output schema, the description covers the essential context: how to handle large result sets (limit+sorted), the exact fields to report for remaining amount, the meaning of densityIsEstimated, and the compact default. It addresses key edge cases (specific spool lookup, unit conversion) that an agent must know to use the tool correctly. This is a complete, production-ready description.

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?

Even with 100% schema coverage, the description enriches parameter meaning. It explains the intended use of sort_by with limit, states that filters are case-insensitive substring matches, and clarifies the semantic distinction between compact modes and the raw vs computed fields (leftGrams vs raw total/left). This is exactly the type of contextual parameter insight the schema cannot convey.

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 opens with a clear, specific verb+resource statement: 'List filament spools with optional filters and sorting.' This precisely defines the tool's function and scope. It also distinguishes this tool from its sibling get_filament, which is explicitly noted as the alternative when a specific spool is named, eliminating ambiguity.

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 guidance is exemplary. It provides explicit 'ALWAYS pair sort_by with a limit' and gives concrete patterns for common queries (sort_by=last_used+limit=10 for most used, sort_by=created+limit=N for recent, sort_by=left for emptiest/fullest). It also clearly states when NOT to use this tool: 'If the user names a specific spool by id or 4-character short id... call get_filament instead.' This is exactly the kind of alternative selection guidance the dimension asks for.

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