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

Annotations already cover read-only, idempotent, non-destructive, and closed-world behavior, so the safety profile is settled. The description adds genuinely new context beyond that: the BM25 ranking method, that snippets come with topic + section citations, and the meaning of the confidence tags preserved in responses. It stops short of stating pagination/truncation behavior for the limit cap, which keeps it at a 4 rather than a 5.

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 purpose and return shape, then usage, then sibling routing, then tag legend — a sensible priority order with no filler sentences. The example list is long but each example maps to a distinct question class, so it earns its space; the block is still dense enough to be slightly heavy for a search 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?

With an output schema present, the description is not obligated to enumerate return values, yet it still explains the citation format and confidence-tag semantics an agent needs to interpret results correctly. Retrieval method, scope (34 topics), usage routing, and query strategy are all covered.

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, but the description adds real guidance the schema lacks: how to phrase the query parameter ('Use specific technical keywords') and how to read the only_tag values via the confidence-tag legend. The topics and limit parameters are left to their schema descriptions, so the boost is partial.

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 and resource ('Keyword search ... across all 34 topics') plus the retrieval mechanism (BM25 relevance ranking) and the return shape (matching sections with cited snippets, tables, verification tags). It explicitly distinguishes itself from siblings by naming the tools that handle numeric data, product equivalents, and budgets.

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?

Explicitly states the best-fit class of question ('Best for free-text questions') with concrete examples spanning code requirements, sizing rules, definitions, estimating, lead times, and testing standards, plus the tactic 'Use specific technical keywords.' It then routes four adjacent use cases to the correct sibling tools, so an agent rarely needs to guess.

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