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

Annotations already declare the safe read-only/idempotent profile, yet the description still adds genuinely new behavioral context: old names like 'Solarban 70XL' are normalized to current names, values are COG rather than NFRC whole-product ratings, discontinued makeups are included by default, and responses carry confidence tags. These provenance caveats materially affect how an agent should interpret and trust results.

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 opening sentence is well front-loaded, but the middle is padded with exhaustive enumerations — twenty substrate tints and roughly twenty product names / '145 makeups' — much of which duplicates the schema's own product and substrate examples. Trimming those lists would make the definition faster to parse without losing actionable information.

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?

For an 11-parameter, zero-required filter tool, the description covers the data domain, the filterable dimensions, an example constraint, name normalization, and the COG-vs-NFRC caveat; with a 100% covered schema and an output schema handling return fields, nothing essential to calling it correctly is missing.

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%, so the schema already documents every parameter and the baseline is 3. The description goes beyond it by giving a concrete filtering example (max_shgc 0.25 for IECC CZ 2) and clarifying that maker/product/substrate accept families and aliases, which helps the agent populate filters correctly.

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?

States a specific verb (filter) and resource (manufacturer center-of-glass performance data for 1 in. IGUs) and scopes it tightly to a curated dataset no sibling covers. An agent can immediately tell this apart from search_glazing_knowledge or cross_reference_glass based on the tabular performance-data scope alone.

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 is only implied through filter examples ('max_shgc 0.25 to meet IECC CZ 2'), not stated as when-to-use versus the sibling tools. There is no explicit routing guidance such as 'use search_glazing_knowledge for narrative answers' or a stated precondition for calling this tool.

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