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

The description discloses that all numbers are read live at request time and that fields are omitted rather than shown as zero or guessed, a key behavioral trait. This goes beyond the annotations (readOnlyHint, openWorldHint, idempotentHint) by explaining the live-data policy and omission handling, which significantly aids the agent in interpreting results.

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 moderately long but well-structured: it starts with the core purpose, clarifies what it is not, lists content, and gives usage guidance. The parenthetical 'CBR41' is internal jargon that may not be useful to all agents, slightly reducing clarity, but it does not detract from the overall structure.

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?

Given no parameters and no output schema, the description covers the essential context: what the tool returns (platform description, metrics), when to call it, and behavioral notes (live data, omission policy). It does not describe the exact response format, but for an overview tool with a dynamic set of fields, this is acceptable. The guidance to call it first when unfamiliar with Defici is helpful.

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?

The tool has zero parameters, so the schema coverage is 100% (empty schema). The description does not need to add parameter semantics, but it does add value by explaining the kind of data returned (platform-scale metrics, module counts). With no parameters, the baseline for parameter semantics is high, and the description maintains it.

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 clearly states the tool returns a platform overview, not a listing search result, and explicitly lists what it includes (agent capabilities, market/category counts, module counts, live metrics). This distinguishes it from siblings like search_listings and get_listing.

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 provides an explicit usage scenario: 'Call this first if you only know Defici as a place with a search_listings tool.' It also clarifies it is not a listings search result, which guides the agent away from using it for listing queries. However, it does not name alternative tools or specify when not to use it beyond that scenario.

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