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

Beyond the annotations, it discloses statelessness, a 32 KB payload cap, a 60 RPM rate limit, authentication via demo mode or L402 payment (25 sats), and a 400 response on invalid input. These are operational constraints an agent cannot get from the schema or annotation block.

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?

Usage intent is front-loaded in the first two sentences with no filler. The second sentence becomes a dense cram of abbreviations (32 KB, 60 RPM, L402, 25 sats, HTTP 400) that reads as a run-on list rather than structured guidance.

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, full annotation coverage, and 100% schema description coverage, the description supplies the remaining operational context (rate limits, payment, error code) needed to call it safely. It stops short of explaining how results are bundled or ranked, but the output schema likely covers that.

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 all three parameters are already documented. The description adds marginal value by stating search_mode's default ('hybrid_semantic_keyword'), but says nothing about max_results behavior or the semantics of the three retrieval modes beyond their names.

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 names specific verbs and resources: query expansion, relevance re-ranking, and extractive snippet bundling over multi-domain semantic search. It distinguishes itself from compile_research_dossier, but does not differentiate from overlapping siblings such as expand_search_queries, rerank_hybrid_rag_chunks, or search_gemini_grounded_web.

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?

It gives an explicit when-to-use clause (retrieving grounded web knowledge, evaluating results across domains, retrieving cited answers) and names a concrete alternative for the deep-research case. It lacks exclusions against the other search/rerank/expand siblings, which the agent must infer.

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