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

While annotations declare readOnlyHint, openWorldHint, and idempotentHint, the description adds essential behavioral context beyond these flags. It transparently discloses cost ('Requires no API key and spends no credits'), important constraints ('up to 20 listings, no cursor, no filter and no search'), and the critical limitation that it never returns a complete set (the capped sample warning). This enriches understanding of its non-deterministic, open-world nature without contradicting any annotations.

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 exceptionally well-structured: a single opening sentence that delivers the core functionality, followed by a compact list of critical constraints, and ending with a clear usage recommendation and a crucial caveat for interpretation of results. Every sentence earns its place, covering what, cost, constraints, when-to-use, and how-to-interpret the output, all in about 90 words, while remaining eminently scannable.

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 zero-parameter tool with no output schema, the description provides complete context for an agent. It covers purpose, cost, invocation prerequisites, output limits, and the crucial semantics of interpreting partial results as an open-world sample. This is particularly important since there is no output schema, and the description successfully communicates the significant caveat about not over-interpreting a short result. The coverage is comprehensive and leaves no knowledge gap for an agent.

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 takes zero parameters, and the schema reflects this with 100% coverage. The description successfully conveys the entire behavior of the tool without needing to explain parameters. It focuses on explaining nuances around the output (the capped, sampled nature) rather than inputs, which is the most important semantic for an agent to grasp here. The 0-param case is handled flawlessly by explaining what the tool doesn't do (no cursor, filter, or search).

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?

Uses a specific verb ('Returns'), a specific resource ('sample of the capability listings currently live on cogDepot'), and enumerates concrete content (offers/wants, category, asking price). Explicitly differentiates itself from the real feed by stating 'This is a PREVIEW, not the feed', setting it apart from sibling tools like cogdepot_discover and cogdepot_get_started.

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?

Provides explicit when-to-use guidance: 'Call it to show what is actually trading, or to judge whether cogDepot is worth an account before getting a key'. It also includes a strong when-not-to-use warning: 'Do NOT conclude from an empty or short result that no matching listing exists - this is a capped sample, not a search.' This directly prevents misuse and implies when to choose an alternative (the real feed).

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