annotate_full

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

With no annotations, the description carries the full burden and does well: it discloses graceful degradation ('failed sub-capabilities are reported per-key under errors with actionable install hints instead of failing the whole call') and the conditional dependency behavior for semantics. It doesn't mention cost/latency relative to individual calls, but the failure semantics are the key behavioral trait an agent needs.

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?

The core purpose is front-loaded in the first line, with the capability list and failure semantics following in descending priority. Three sentences with essentially no filler; only minor overhead from the inline code markup and a slightly dense second sentence.

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?

An output schema exists, so the description needn't explain return values, and it correctly focuses on composition and failure handling. The main gap is the undocumented `lang` parameter; otherwise an agent has enough to invoke this correctly for a 3-parameter aggregation tool.

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 0% across 3 parameters, so the description must compensate. It does explain `with_semantics` well (enables seme_lookup/wordnet when libraries are installed), and `text` is self-evident, but `lang` (default 'auto') is never mentioned — its accepted values and auto-detection behavior are undocumented anywhere.

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 opens with a specific verb and resource ('run every available capability in one call and merge the results') and then enumerates the exact sub-capabilities bundled (tokenize/pos/ner/keywords/sent_split/openie). This clearly distinguishes it from every sibling tool, which each provide one of those capabilities individually.

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?

'One round trip instead of seven' gives the agent a clear economic motive to prefer this over chaining the individual sibling tools. However, it does not state when NOT to use it (e.g. when only one capability is needed, the extra cost of the full bundle), leaving that inference to the agent.

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