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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), so the description's added value is the return contract: answerable/confidence signal, corpus_version, stable chunk IDs, license and source URL fields, and next_actions. That is meaningful context beyond the annotations, though it omits rate limits, corpus scope, or error behavior.

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-loads purpose, then when-to-use, modes, options, and return shape in a clear progression with no fluff. It is dense and the verbose return-field enumeration is justified by the absence of an output schema, though 'auto (default, both)' mildly repeats the schema default.

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 no output schema and only one required parameter, the description correctly compensates by spelling out the response shape and the confidence/answerable signal. It covers modes, options, and routing, leaving only edge cases like empty results, pagination behavior, or failure modes unaddressed.

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 baseline is 3, but the description adds real meaning to the mode enum (schema only says 'Default auto', while the description explains what keyword and semantic actually do). Lang, limit and snippet_chars get no added depth beyond the schema, keeping it from a 5.

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 ('Unified CyberLibrary search') and goes further to describe the mechanism (BM25 + neural semantic fusion via RRF) and the output (passages with chunk IDs, citations, confidence). It does not explicitly name the sibling alternatives it overlaps with (cyberlibrary_semantic_search, cyberlibrary_fulltext_search, cyberlibrary_search_passages), so differentiation from those is left to inference.

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?

Explicit 'When to use: first choice when you do not want to decide between keyword and semantic search' gives a clear selection rule, and the mode descriptions (keyword for exact terms/names, semantic for paraphrase/theme) extend that into in-tool routing. No when-NOT-to-use or named sibling fallbacks, so it stops short of a 5.

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