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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the burden is light, and the description still adds a genuinely non-obvious trait: the call returns the CSV only when it is 500 rows or fewer. It stops short of saying what happens above that threshold, which is the one behavioral detail an agent would still need.

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 tightly packed sentences that front-load the core operation and then the optional behaviors. The closing 'POST JSON: files is an array' restates schema content and is the one clause that doesn't earn its place.

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 no output schema and only three parameters, the description covers enough to invoke correctly, including the row-count return condition. The gap is that the over-500-rows path is undefined — the agent doesn't know whether the result is truncated, empty, or an error.

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 baseline is 3, and the description earns above it by explaining the semantics of the boolean flags — dedupe means duplicate emails, addSource adds a column naming the originating file — and by clarifying that column matching is semantic (Email/email_address/E-mail). The trailing 'POST JSON: files is an array' adds little beyond the schema.

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 (merge) and resource (lead CSVs), plus the distinguishing behaviors: fuzzy column-name matching, optional email dedupe, and an optional source-file column. What's missing is differentiation from the adjacent sibling tools clean_csv and convert_csv, which an agent could easily confuse with this one.

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 implied by the described behavior ('several' files, optional dedupe), but there is no explicit when-to-use or when-not-to-use guidance and no reference to clean_csv/convert_csv, which handle overlapping CSV-manipulation territory. The agent must infer the routing decision itself.

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