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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open-world), so the bar is lower. The description adds genuine value by disclosing the analytical shape of the response (histogram, top-N, averages) and the upstream report ID, though it omits potentially useful traits such as whether results are scoped to currently-open cases only or pagination behavior.

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-loads the core purpose, then outputs, then the questions it answers—a sensible order with little waste. It is slightly list-like, but every clause adds selection 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?

With an output schema present and read-only annotations, the description needn't detail return values, and it nonetheless characterizes them. The main residual gap is the undocumented parameters (as_of_date, property_ids), which the schema does not compensate for.

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 0%, so the description must carry parameter meaning, and it largely doesn't. It hints at top_n ('top-N oldest cases') and portfolio ('for a portfolio'), but as_of_date and property_ids are never mentioned, and no formats, defaults, or filtering semantics are given for any of the four.

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 (analyze) and resource (open evictions) with scope ('for a portfolio') and even cites the source report. The enumerated outputs (per-property count, balance at risk, days in stage, reason histogram, top-N oldest) let an agent distinguish it from sibling analyze_* tools like analyze_delinquency without opening the 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?

The 'Answers:' clause gives concrete question patterns (count of open evictions, balance at risk, longest-stuck cases, reason breakdown) that clearly signal when to reach for this tool. It stops short of naming alternatives or exclusions, so it's clear context without explicit routing.

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