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

Adds substantial context beyond the annotations: the model (EmbeddingGemma 2) runs locally with no API key, first use downloads ~350 MB (a real latency/first-call cost the agent should anticipate), OCR-unavailable articles are included (coverage envelope), and similarity_score is only comparable within a single query. That last point is a critical interpretation caveat that no annotation or schema conveys.

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?

Four short sentences, each carrying distinct load: scope, language, execution/dependency, and result-interpretation. The most consequential caveat (similarity_score cross-query incomparability) is placed last, after the agent knows what the tool is, and nothing is repeated from the schema.

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, the description does well to name similarity_score and its interpretation limit. It leaves gaps for a 6-parameter tool: no sense of result shape, whether filters are applied pre- or post-retrieval, or what happens when nothing semantically matches. Strong but not exhaustive for a search tool with no declared return structure.

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 83%, so the schema already documents query, limit, country, dates and newspaper — baseline 3 applies. The description adds only "any language" for the query, which the schema already states, and says nothing about how country/date/newspaper interact with semantic ranking or about the max-from-default relationship for limit.

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 and scope: semantic search over title + full text, including OCR-unavailable articles. This implicitly separates it from the lexical `search_articles` and from `semantic_search_images`/`semantic_search_publications`, but it never names those siblings or says explicitly that this is the semantic (not keyword) counterpart for articles. A competent agent can infer the distinction, so 4 rather than 5.

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?

"Query in any language" gives real context about acceptable input, and the presence of country/date/newspaper params implies filterable browsing. However there is no explicit when-to-use-this-vs-`search_articles` guidance, no statement that semantic search suits conceptual/fuzzy queries while lexical suits exact terms, and no note about when the local model download cost is worth paying. Usage is implied, not stated.

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