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

Annotations flag destructiveHint=true and idempotentHint=true, and the description explains exactly why: 'Lists REPLACE what is saved, so pass the complete list, not an addition' — i.e. it discloses what gets destroyed. It further adds non-obvious costs ('Uses AI credits'), precedence rules ('fields passed explicitly win over it'), and an anti-hallucination constraint for application_answers.

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?

Front-loaded with the core action, then prerequisites and guardrails in descending importance; every clause carries actionable content. It is a single dense paragraph long enough that the 'REPLACES' rule and the get_account prerequisite are easy to skim past, and the application_answers field enumeration partially duplicates the schema.

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 15-parameter, zero-required, destructive mutation with a nested object, the description covers the essential unknowns: precedence between free-text and explicit fields, list replacement semantics, read-before-write, when to invoke, and the no-guessing rule. An output schema exists, so return values need no explanation.

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 the baseline is 3; the description goes beyond it by defining the interactive semantics of `description` (plain-language input, overridden by explicit fields, consumes credits) and the replace-not-merge semantics of every list field. The nested application_answers object is only summarized (its field list duplicates the schema) without per-field guidance such as date formats.

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?

Opens with a specific verb+resource ('Set what GetMattered hunts for on the user's behalf, and re-run discovery immediately') and enumerates the exact preference dimensions it controls. It also explicitly separates itself from getmattered_get_matches and getmattered_get_account, so an agent can distinguish it from all siblings.

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 explicit when-to-use ('Only call this when the user asks'), a required prerequisite ('Read the current preferences first with getmattered_get_account'), and an explicit when-not with the correct alternative ('Do not use it to search; use getmattered_get_matches with query'). Nothing is left to inference.

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