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

Annotations only say readOnlyHint=false/destructiveHint=false/openWorldHint=false; the description adds substantial context beyond that: no money, nothing posted to the marketplace, a 20-second processing window, the same acceptance tests as a paid task, per-IP rate limiting, and a fixed returned bundle (output, checks, all_passed, quote, next steps, try_token). That is exactly the behavioral detail an agent needs before calling a write-flagged tool.

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 value proposition and stays within a single dense paragraph with no filler, but it crams return values, rate limits, fallback behavior, and enum samples into one run-on block, making it slightly harder to scan than it could be.

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 no output schema, the description compensates by enumerating the returned fields and flagging all_passed as the acceptance signal, and it covers limits (25 records, 20s, 5/hour/IP) plus the unsupported-field fallback. Nothing an agent needs to call it correctly is missing.

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 schema already documents records (1-25, domain field), key_fields, and the enrich_fields enum. The description restates these and adds only a light cross-field hint (title as string with min_fill_ratio below 1), which the schema partially encodes already; baseline 3 applies when the schema carries the weight.

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 action (free enrichment trial with no API key), the exact scope (up to 25 records with a domain field, four allowed enrich fields), and clearly distinguishes itself from the paid path (post_enrichment_task / 'Nothing is posted to the marketplace'). An agent can tell immediately this is the sandbox/trial variant rather than the real task-posting tool.

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 preconditions (records need a domain field, enrich_fields limited to resolved/has_mx/https_ok/title) and an explicit exclusion path: other fields answer try_unsupported and you should post a real task instead. It also names the rate limit (5 runs per hour per IP), which is the practical gate on when to call it.

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