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

Annotations already declare readOnly and openWorld. Description adds significant behavioral context: newest-first ordering, nextCursor pagination, and the data quality caveat that valueEur is null in ~65% of exits. This goes beyond the structured annotations and helps manage expectations about data completeness.

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?

Three sentences, front-loaded with purpose, then filters, then a data caveat. Every sentence adds value; there is no redundancy or fluff. It is concise yet packs essential information.

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?

Provides purpose, ordering, pagination, filtering options, and a notable data caveat. With no output schema, it does not list full response fields, but it covers the essential information an agent needs to invoke and interpret results. A slight gap on response structure is acceptable given the schema provides parameter details and the description highlights a key field (valueEur).

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?

Input schema already covers 80% of parameters with descriptions (to, from, country, after). Description reinforces date window and country filtering but adds minimal new parameter semantics. The limit parameter lacks a textual description but has min/max constraints, leaving it reasonably inferable. With high schema coverage, baseline 3 is appropriate.

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?

Description clearly states it searches European tech exits and M&A (acquisitions, IPOs), sorted newest first with cursor pagination. It distinguishes from sibling search tools (companies, investors, rounds) by specifically targeting exits.

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?

Explicitly says 'use it for "European exits"' and describes filters (date window, country), giving clear context for when to apply this tool. Does not explicitly name alternatives or exclusions, but the scope is well-defined and distinct from siblings.

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