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

Annotations already declare readOnlyHint=true, but the description adds substance beyond that: the newest-first ordering, the opted_out semantics (true when the person sent STOP), the hard constraint never to contact them, and the prerequisite 'Needs inbox access.' Those are behavioral facts an agent cannot derive from structured fields and are critical for safe downstream action.

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?

Four tight sentences, front-loaded with what the tool returns and immediately followed by filters and safety constraints. The only dead weight is the near-duplication between 'never contact them' and 'Never message a lead unless the user asks.'

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, the description responsibly enumerates the returned fields and the default window, and it covers filters, ordering, auth prerequisite and consent safety. It does not state what happens with the limit parameter or whether results are truncated beyond 200, which would matter for exhaustiveness-sensitive use.

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%, with defaults, ranges (1-90 days, 1-200 limit) and examples already documented. The description maps concepts to parameters ('filter by account, keyword or has_email') and clarifies what 'the email they gave' means for has_email, but adds little syntax or format detail beyond the schema. 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 resource (people an automation answered), the default time window, sort order (newest first), and exactly which fields come back (handle, keyword, post, email). This distinguishes it clearly from siblings like sprkly_list_inbox_threads, which list conversations rather than automation-answered leads.

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 concrete selection criteria (filter by account, keyword, has_email) and an explicit prohibition (never contact them; never message unless the user asks). It stops short of naming the sibling tool an agent should prefer when it actually wants to reply to a lead, so routing to reply_to_dm is only implied.

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