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

Annotations only declare the generic safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=false), so the description carries real added value: it discloses that existing participants are returned unchanged, that enrollment bypasses affiliate review, and that a new participant may be silently created with affiliateStatus: APPROVED. It does not mention auth/permission requirements or rate limits, keeping it out of the top tier.

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?

The definition is a dense but front-loaded paragraph that leads with the core add-or-fetch behavior and then layers the conditional enrollment rules in a logical order. Sentences are long and information-packed rather than padded, with no filler, though the final conditional sentence is somewhat convoluted.

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?

An output schema exists, so return values need not be documented, and the description handles the campaignId default and enrollment branching well. Still, for a 12-parameter mutation tool at 25% schema coverage, several parameters (referralStatus, fingerprint, mobileInstanceId) and any permission/scope requirements remain undocumented, leaving gaps an agent may hit.

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 only 25% across 12 parameters, and the description compensates well for the hardest ones (isAffiliate, referredBy, campaignId fallback to GROWSURF_CAMPAIGN_ID, email as the lookup key). But it leaves metadata, firstName, lastName, ipAddress, fingerprint, mobileInstanceId, and the referralStatus enum entirely unexplained, so it only partially fills the coverage gap.

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?

The description opens with a specific verb+resource and a lookup key: 'Add or fetch a participant by email,' and immediately clarifies upsert semantics ('Existing participants are returned unchanged'), which behaviorally distinguishes it from growsurf_get_participant and growsurf_update_participant. It stops short of naming a sibling or stating the read-only alternative, so it falls just below the top tier.

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?

It gives explicit routing context for the tricky cases: 'trusted direct enrollment and bypasses the public application review flow for affiliates,' plus conditional rules for isAffiliate and referredBy. However, it never says when to prefer this tool over growsurf_get_participant (pure read) or growsurf_update_participant (modify existing), leaving the main sibling-selection decision to inference.

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