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

With no annotations, the description carries the full burden and does so generously: it discloses the scoring model (all words must match, matching all doubles the score, extra words widen rather than narrow, name matches outweigh description matches), the 100-item cap, deterministic/stable paging, and a startup-fixed registry so no operation is dropped or duplicated across pages. These are exactly the non-obvious behaviors an agent needs to query well.

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 single most important fact (unlisted operations exist) and organized by invocation mode. It loses a point for the changelog aside ('the AND-then-fall-back-to-OR behaviour this said before was removed in ef47aa9ab'), a commit hash that costs attention and gives an agent nothing actionable.

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?

No annotations and no output schema exist, so the description must stand alone, and it mostly does: it explains what browsing/tag/query return (areas with operation counts, ranked matches) and how to page through large result sets. It could say a bit more about the shape of a returned match (name, description, tag) before handing off to describe_operations, but the workflow is complete enough to call correctly.

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%, so the description must compensate, and it defines all four parameters semantically: tag lists one area, query searches by keyword, limit is capped at 100, and offset is driven by next_offset for paging. It stops short of stating the defaults (25/0/empty string) and whether tag and query can be combined, but the gap is minor.

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?

Opens with a specific verb and resource ('Search EVERY operation this server offers') and immediately carves out the scope that makes it unique: operations not present in the visible tool list. It names concrete examples (payroll, VAT returns, year-end close) and distinguishes itself from describe_operations/call_operation by pointing to them as the follow-on steps.

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?

Prescribes exactly when to use it ('Search here before concluding that Zeno cannot do something') and enumerates the three invocation modes: no arguments to browse tags, tag to list one area, query for keyword search. It also routes the agent onward via describe_operations then call_operation, giving a complete decision path with no inference required.

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