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

Annotations already declare readOnly, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuinely non-obvious semantics: what each result contains and, crucially, that 'score' is 0–100 where 100 means fully vegan — an interpretation an agent could easily get wrong. It omits ranking order and whether matching is case-insensitive.

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 tight sentences: the action first, then the return shape. Every clause carries information (match fields and score semantics) with no restatement of the tool name or filler.

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?

Return values are described despite there being no output schema, and the score scale is explained, which is the highest-risk ambiguity. The remaining gap is behavioral sizing — no mention of the default 10 / max 25 limit or result ordering — but for a simple name lookup this is close to complete.

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 50%: 'query' is described inline (restaurant name or part of it), but 'limit' has only a default and a 1–25 range with no explanation. The description never mentions result count or the 25 cap, so it does not compensate for the coverage gap; baseline 3 applies for a two-parameter tool.

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: 'Search restaurants by name', which is precise about the lookup mode (name, not location or city). It does not, however, differentiate itself from siblings like places_near or city_vegan_places, leaving the agent to infer the distinction.

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?

Usage is only implied by the phrase 'by name' — it hints that this is the tool to use when you already know a restaurant name, versus browsing by city or proximity. There is no explicit when/when-not statement or named alternative, so the routing decision rests on inference.

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