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

Annotations already declare destructiveHint=true and idempotentHint=false; the description adds the concrete consequence ("adds to the contact's total spent") and a specific irreversibility caveat ("cannot be undone with this server"), which is exactly the context annotations cannot convey. It stops short of stating permissions or how the aggregate is affected on failure.

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, zero waste, front-loaded with a WRITE marker so the agent immediately knows the operation class. Every sentence carries distinct information: intent, side effect, return value.

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?

For a 4-parameter mutation with full schema documentation and clear annotations, this covers purpose, side effect, irreversibility, and return value. Minor gaps remain: no note on required fields (delegated to schema) or what happens if the contact does not exist.

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% — every parameter has a description, examples, format hints, and bounds — so the description correctly does not duplicate them. Its parenthetical "(name, amount, date)" merely echoes three of the four fields without adding format or default semantics (e.g. `created_at` defaulting to now is only in 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 ("record") and resource ("a purchase or donation against a contact") plus the key identifying fields. No sibling tool performs contributions, and the GraphQL mutation name (`createCustomContribution`) pins down exactly which backend operation this is.

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?

The context of use is implied — logging a purchase or donation for a contact — but there is no explicit "use this when…" framing, no prerequisite (contact must already exist), and no mention of alternatives or when-not to use it. Adequate, but the agent has to infer the trigger.

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