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

Annotations declare non-read-only, non-idempotent, non-destructive; the description adds the missing behavioral payload by explaining the return value ('a filename served from the CDN'), which annotations cannot express. It does not say whether repeated calls generate duplicate export files (relevant given idempotentHint=false) or whether the file expires, so a small gap remains.

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 short sentences, zero filler: capability first, return shape second, disambiguation third. Nothing to trim.

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 handling is covered despite no output schema, and all filters being optional is visible in the schema. It never states what happens when no filters are supplied (full export of all leads, potentially large), which is a meaningful omission for an export tool with zero required parameters.

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 description coverage is 100%, so the schema already documents all three filter parameters including the enum source for tags and campaign ids. The description only restates the filter names collectively and adds no format, default, or combination semantics 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 and resource ('Generate a CSV of leads') plus the available filters, and explicitly distinguishes itself from `lead_list` (in-conversation reading) and `campaign_export_stats` (aggregate numbers). An agent can tell exactly what this produces without opening the 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?

Gives an explicit trigger ('Use it when the user wants a file') and names two siblings with the conditions that select them instead. Routing is unambiguous.

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