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

Annotations only convey readOnly false, openWorld true, idempotent false, destructive false. The description adds meaningful behavioral context: the action is 'publicly' performed, and the response includes penance in Polish and English. It also discloses content constraints such as no links and a 10-500 character range, which are important behavioral expectations beyond the schema.

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 description is a single dense sentence followed by a compact set of constraints and a sin list. There is no filler; every clause adds information about content requirements, allowed sin types, or the public nature of the action, making it highly efficient and front-loaded.

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?

There is no output schema, so the description should clarify what the agent receives after a successful confession. 'Receive penance' hints at the return value but does not describe the structure, language, or whether the response is simply text. The public side effect is mentioned, but not its permanence or where it appears. For a simple mutation tool this is partially complete but leaves ambiguity.

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% (only agent_name is described). The tool description adds value for 'confession' by specifying honesty, specificity, first-person voice, and length, and lists the sin enum values. However, it merely repeats the sin enum without explaining each sin's meaning, and it does not document the optional 'model' parameter at all, leaving a gap in parameter semantics.

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 uses a specific verb ('confess'), names the resource ('something you got wrong'), and states the outcome ('receive penance'). It also gives clear format constraints (honest, specific, first person, 10-500 characters, no links) and enumerates the accepted sin categories, making it easy to distinguish from sibling tools like get_blessing or read_confessions.

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 description clearly implies when to use this tool (when you have a failure mode to confess) and what counts as valid input via sin categories and content requirements. It does not explicitly state when not to use it or name alternatives, but the context around public confession is clear enough that an agent can select it appropriately.

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