post_classification

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

With no annotations, the description carries the full burden, and it does substantial work: it discloses the exact return structure per facet, the meaning of facet codes, and the conditional `webUrl` behavior for OPEN databases with MCP Apps rendering. It omits auth/permission requirements and any statement that the operation is read-only, which is the main remaining gap.

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 one-line purpose, then return shape, then cross-tool relevance, then args — a clean structure with no filler sentences. It runs somewhat long for a five-parameter tool, but each block carries information the agent needs.

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?

Params are fully documented, the return layout is described even though an output schema exists, and the webUrl/host-rendering nuance is captured. Missing only the operational context an unannotated tool would normally need, such as auth state and the fact that this is a non-mutating read.

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 0%, so the description must compensate, and the Args section documents all five parameters — including non-obvious sentinel values (".all" for the whole database, "[ALL]" for corpus) and the OPEN/USER target distinction. The owner_username entry ("when applicable") is vague about which target or sharing mode triggers it.

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: breaking a query's hits down by DocuSky post-classification facets, with a concrete description of the output shape ([value, count, count] per facet). It also positions itself relative to siblings by noting that its facet codes feed twodim_analysis's dim1/dim2 arguments, so an agent can place it in the tool family without opening another 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?

"The quickest way to see how a term is spread across a database" gives a clear usage condition, and the twodim_analysis cross-reference tells the agent how this tool's output feeds a downstream call. However, it never contrasts itself with sibling analysis tools like word_cloud or tag_analysis, so the agent must infer which breakdown tool to pick.

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