localgate_search

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

With no annotations, the description carries the full behavioral burden. It does add genuinely useful non-obvious context — the retrieval is hybrid and all data stays local — but omits whether the call is read-only, what happens when nothing is indexed, latency/cost characteristics, and the shape of results.

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?

Two sentences, no filler, with the core action stated first and the corpus/privacy detail following. Every clause earns its place.

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?

For a simple 2-parameter, no-output-schema search tool this is nearly adequate, but it never indicates what a result contains (paths, snippets, scores) or how results relate to the localgate_get_document follow-up, leaving a small but real gap.

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% for both parameters, so the baseline of 3 applies. The description adds no syntax, ranking, or defaulting detail beyond what 'query' and 'top_k' already state in the schema.

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 gives a specific verb+resource ('Hybrid search over the user's local indexed files') and even names the retrieval mechanism (full-text + vector) and the corpus (notes, PDFs, docx, source code, chat exports, OCR'd images). It is clearly distinct from localgate_status and localgate_get_document without naming them, so it falls just short of the explicit sibling differentiation a 5 requires.

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?

There is no when-to-use guidance at all: nothing says to call this first and then retrieve full documents via localgate_get_document, nor whether localgate_status must be checked to confirm the index exists. The agent must infer routing from the sibling names alone.

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