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

Annotations already cover safety (readOnly, non-destructive), but the description adds substantial behavioral context beyond them: credit cost model per workspace tier, free rows and re-pulls, that this tool never spends credits, and that it returns a quote instead of charged rows past the free allowance, with an instruction to ask the user before the paid run. This is exactly the kind of context annotations cannot convey.

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 scope, then alternatives, then filters, then paging and pricing. Efficient and well-ordered. The pricing/credit paragraph is long but earns its place given the quote workflow; minor density cost.

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?

An output schema exists, so return values needn't be explained, and the description still gives the essential result shape ('summary rows, newest first, up to 25'). For an 11-param read tool with a non-trivial credit/quote workflow, everything an agent needs to call it correctly and safely is present.

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 64%, so the description carries some burden. It enumerates filter categories (borough, foreclosure stage, equity, case age, recently added, market value, amount owed) and documents return paging (up to 25 per call, default 10, page with offset), which maps to several params. It doesn't add units/format details for amountOwedMin/Max or marketValueMin/Max, leaving those param descriptions thin, so not a full 5.

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+resource+scope ('Searches NYC properties in preforeclosure only: lis pendens foreclosure filings in Manhattan, Brooklyn, Queens, the Bronx and Staten Island'), and explicitly distinguishes from siblings find_nyc_property and the national search tools. An agent can route correctly without opening a 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?

Explicit when-to-use and when-not-to-use: use find_nyc_property for a single NYC address, use national search tools for filtered or non-NYC searches. The pricing/quote workflow also tells the agent exactly when to call run_nyc_preforeclosure_search with the quote_id.

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