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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the description sensibly spends its words on non-obvious behavior: nothing is submitted, documents must be uploaded via the REST API or the site rather than this server, retries are made safe by reusing an idempotencyKey, and the result carries `state` and `nextAction`. That is meaningful context beyond the annotations. It stops short of describing failure modes or error behavior, which keeps it at a 4 rather than a 5.

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 purpose and the 'nothing is submitted' boundary are front-loaded, then constraints, retry safety, the exclusion, the next step, and the auth requirement follow in order. Every sentence carries a routing rule, a constraint, or a prerequisite; none is filler, despite the description being longer than average.

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 12-parameter nested-object mutation with no output schema, this definition supplies everything an agent needs: required inputs, the non-submission guarantee, the idempotency contract, the auth requirement, the sibling to avoid, and a summary of what the response contains (`state`, `nextAction`). No output schema exists, but the description covers the return shape at the level needed to proceed.

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 100%, so the baseline is 3 and the schema already carries the field-level meaning. The description nonetheless adds value by enumerating the five required fact groups in plain language and by reinforcing two schema-level instructions that are easy for an agent to skip: always pass and reuse `idempotencyKey`, and treat attestations as the person's own statements rather than something to invent.

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 states a specific verb and resource ('Creates a draft case in the person's account') and immediately bounds the scope with 'Nothing is submitted.' It distinguishes itself from siblings by naming evictions_update_case as the wrong tool for existing cases and evictions_validate_case as the next step, so an agent can route correctly without opening another schema.

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 an explicit trigger ('when the person wants to start an eviction case and has given you its facts: the ground, where the case starts, the property, the parties and their own attestations'), an explicit exclusion ('Do not use this to change a case that already exists (use evictions_update_case)'), a follow-on action (evictions_validate_case), and a prerequisite (sign-in or an API key). Nothing about when to select this tool 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.