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

Annotations already cover safety (readOnly, openWorld, non-destructive), yet the description adds substantial operational context: results are researched from public websites and cached, research.status values ('queued', 'limited', 'paused', 'unavailable') each have a defined meaning, and new listings appear within minutes. It also discloses data provenance ('nothing is invented') and plan gating for decision-maker names/emails, which no annotation conveys.

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 purpose, then behavior, then the soundcheck linkage — a sensible ordering. The 18-value category list is duplicated verbatim from the schema enum and consumes a large share of the text without adding information, which is the main waste.

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?

For a read-only search with an output schema and rich annotations, everything an agent needs is present: what is searched, what a result contains, why results may be partial, what each research status implies, and how to continue with sibling tools. No material gap remains.

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%, so the schema documents city/region/country/query/limit/offset/category on its own. The description adds real semantic value by explaining that a category-plus-city combination that has not been researched is queued and returns partial results — behavior the schema only hints at for category alone. It says nothing extra about paging or free-text matching, so it is not a full 5.

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 ('Find event businesses'), enumerates the covered business types, and names the filter dimensions (category, city, free text). It is clearly distinguishable from siblings like search_places or get_business, which operate on places/single records rather than a categorized business directory.

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?

Gives clear conditions for the tool's interesting states (unresearched category+city is queued, 'limited'/'paused' means cached results only) and routes the agent onward: on_soundcheck=true slugs work with get_public_org and request_booking. It stops short of an explicit 'use get_business for full details instead' exclusion, so it is clear context without full when-not guidance.

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