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

Annotations only declare readOnlyHint and openWorldHint, so the description carries the interesting burden and delivers: it discloses the data source (public Bing video HTML/async pages) and a concrete failure mode (503 when Bing serves a challenge page or unusable HTML). This is real operational context an agent can't get from structured fields, though it doesn't cover throttling beyond the 503 note.

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-loads purpose, then defaults, then failure behavior, then the sibling pointer – a sensible order with no filler. The Query/Count restatement is mildly redundant with the schema but not wasteful.

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 an output schema present, return values needn't be described, and annotations cover the safety profile. The description covers purpose, locale defaults, data provenance, and a failure mode, leaving little an agent needs missing – only multi-page/pagination behavior goes unmentioned.

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 already documents all five parameters. The description restates Query and Count almost verbatim from the schema and adds the locale default (country=us, lang=en-us), which maps to the Country/Language params. Net added value over the schema is minimal, 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?

States a specific verb and resource ('Returns normalized Bing video search results for a query string'), and explicitly distinguishes itself from bing_search by naming the sibling to use for web results. An agent can tell it apart from bing_images/bing_news by the 'video' resource without opening any schema.

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?

Names one alternative with its selecting condition ('Use bing_search to search Bing web results'), which routes the agent correctly. It gives clear context for use but stops short of addressing the other Bing verticals (images, news, suggest) that also compete for similar queries.

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