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

Annotations already cover the read-only/idempotent safety profile, and the description goes well beyond them: it enumerates every returned field with its meaning (best_score as cosine of the single best passage, score_sum as summed passages, matched_vectors_count), explains the rank_by tradeoff, notes language handling, and gives the index_unavailable fallback. This is the kind of behavioral context annotations cannot express.

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 key distinction ("OBJECTS, not passages") and every clause carries information. It is a dense single paragraph with heavy dash usage, which slightly hurts scannability, but nothing is redundant enough to cut.

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?

There is no output schema, and the description compensates by documenting the result shape field by field, including the object_pk handoff to get_detail_* tools. Combined with error handling and ranking guidance, 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 coverage is 100%, so baseline is 3, but the description adds real meaning the schema lacks: rank_by "score_sum" is explained as favouring objects matching in many passages versus "best_score" for the single closest passage, with the recommendation to use best_score to find the exact work a text is about. It also clarifies that the query can be any language while the underlying texts are English.

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?

Names the specific verb (semantic search) and the objects returned (artworks, artists, museums, articles), and explicitly contrasts with siblings: "returning OBJECTS, not passages" and "with a name or keywords, use search_fts". An agent can distinguish it from search_sections_semantically and search_fts without opening a schema.

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 explicit when-to-use ("when you have a text and want the objects it is about") and two named alternatives with the conditions that select them: search_fts for names/keywords, search_sections_semantically for answering passages. It also provides a recovery path for the index_unavailable error, which is unusually complete routing guidance.

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