semantic_search

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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description adds meaningful context beyond them: it operates only on a local index, returns empty results on an unpopulated index, and requires the [pro] dependency install. It does not say what happens if both query and paper_id are omitted or both supplied — notable since zero parameters are required.

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 the core capability and the local-only constraint, with the dependency note demoted to the end. The install command is long but genuinely actionable; overall wording is tight with minimal redundancy.

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?

Covers the index prerequisite, the discovery/download workflow, and the pro install, which is most of what an agent needs. However, with no required parameters and no output schema, the description leaves open how mode selection is enforced and what results contain (fields, similarity scores, limits).

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 all three parameters are already documented, which sets the baseline at 3. The description adds example query phrasing ('attention mechanisms for long sequences') and clarifies that paper_id selects a similarity-to-paper mode, but adds nothing about max_results or the interaction between the two mode parameters.

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 similarity search over papers you have already downloaded locally'), and explicitly distinguishes the two query modes (free-text vs. paper_id similarity). It also names search_papers as the different sibling for arXiv discovery, so an agent can separate the two 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 an explicit workflow: use search_papers to find papers on arXiv, download_paper to add them to the local index, then this tool. It also states the negative condition — empty results if nothing has been downloaded — and the pro-dependency requirement, so the agent knows when not to call it.

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