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

With readOnlyHint already declared, the description still adds a lot: no auth required, 40 questions/hour per token plus a shared anonymous budget, the advice to pass a token, and the 'at most 3 hits per talk' cap. It also states retrieval-only behavior and describes the exact return payload, which annotations do not cover.

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?

Purpose and the retrieval-only constraint are front-loaded, followed by budget then a compact Args/Returns block. It is dense and readable, though the Args restatement duplicates the schema and the Returns enumeration is long for a single line.

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, so enumerating the return fields (slug, talk_title, series, speaker, similarity, slide, snippet, deep_link, detail_link, via) is genuinely necessary and included. Auth and rate-limit behavior, the per-talk hit cap, and the retrieval-only nature 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 both q and k are fully documented with ranges and default in the schema itself. The description's Args block largely restates those constraints (1-500 chars, 3-25, default 10) rather than adding new semantics, so the baseline of 3 applies.

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: semantic search over all Immersive Commons talks returning matching slides. It also distinguishes itself from the sibling list/get tools by framing itself as the '/presentations search box' equivalent, and it explicitly says it is retrieval only, not a generated answer.

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?

Clear context for use (find slides by meaning, then read snippets and follow deep_link) and it explicitly excludes the generated-answer expectation. It does not name ic_presentations_list or ic_presentations_get as the alternative for enumerating talks, so the agent must infer that routing itself.

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