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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), but the description adds genuinely useful behavior: BM25 relevance ranking, the 32-topic search scope, and the confidence-tag legend ([V], [V-mfr], [UNVERIFIED], [inference], [Expert]) that an agent needs to interpret results correctly. It stops short of stating pagination/limit behavior or ranking tie-breaks, so it is not exhaustive.

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?

Front-loaded with the core capability and ranking method, then usage classes, then alternatives, then tag legend — a sensible information hierarchy with no filler sentences. The verbose example list and inline sibling routing make it dense; it is longer than strictly necessary but every clause carries signal.

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?

An output schema exists, so return values need not be enumerated, yet the description still characterizes the return shape (cited snippets with topic + section id, tables, tags). Combined with full schema coverage, explicit sibling routing, and tag semantics, an agent has everything needed to call and interpret this tool correctly.

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 description coverage is 100%, so the baseline is 3. The description adds meaning on top: it advises 'use specific technical keywords' for the query and explains what the verification-tag values signify, which illuminates the only_tag enum beyond the bare enum strings. It does not explain topic-number scoping or limit interaction, so it is only slightly above baseline.

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+resource (keyword search across the glazing knowledge base), names the ranking mechanism (BM25), the corpus size (all 32 topics), and what is returned (cited snippets, tables, verification tags). It explicitly differentiates itself from four sibling tools by naming each one and the data class it owns.

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?

Gives both when-to-use ('Best for free-text questions') with concrete example query classes (code requirements, sizing rules, definitions, estimating red flags, lead-time drivers) and when-not-to-use, routing numeric data to lookup_glass_performance, equivalents to cross_reference_glass / cross_reference_aluminum_system, and budget questions to budget_price_range. Nothing is left to inference.

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