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

Annotations already declare readOnly, idempotent, closed-world, non-destructive, so safety is covered. The description adds that results are names/doors/pours and explicitly excludes stories and headcounts, which is genuine behavioral context. However, it's expressed in metaphor rather than stating ordering, recency window, or anything operational.

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?

It is short, but the telegraphic style ('Names, doors and pours. Never stories.') makes the reader decode meaning rather than absorb it. Nothing is wasted, yet front-loading is weak — the exclusions arrive before any positive scope statement.

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?

With rich annotations, a 100%-covered one-parameter schema, and an output schema, the structured fields carry most of the load. The description's remaining job is to disambiguate from siblings, and it only does so obliquely, leaving the boundary with regulars/my_tab unclear.

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% and the single 'limit' parameter is documented with bounds in the schema. The description adds nothing about the limit (no default, no cap guidance), so baseline 3 applies.

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 title and description both say 'recent orders', and 'Names, doors and pours' gestures at the returned fields (patron names, entry/exit, drinks). But it never states the verb/scope plainly, so an agent must infer that it reads the latest bar orders. It is not a tautology, but it's far from a specific verb+resource statement.

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?

Only the fragment 'Not a headcount' hints at an exclusion (presumably vs. a person-count view like regulars), and 'Never stories' rules out narrative detail. There is no explicit instruction on when to use this instead of siblings such as my_tab, regulars, or whats_playing.

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