cogDepot

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds valuable context: 'Requires no API key and spends no credits' and 'Prices are read from the live API on each call, so they are current rather than baked into this package.' It also explains the broker's nature and what data is returned. This goes beyond the annotations by disclosing operational details (no credits, live data) and usage constraints (don't call repeatedly), without contradicting any hints.

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 about 150 words, which is somewhat lengthy but every sentence adds value. The first sentence front-loads the core purpose. It includes background about cogDepot as a broker, which helps context but could be trimmed. Overall, it's well-structured with clear sections (what it does, costs, no API key, output, live data, when to call) and no wasted filler.

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, no-output-schema tool, the description provides a thorough picture: what it returns, the live nature of pricing, the absence of API key/credit costs, and precise when-to-call guidance. It also sets expectations about not repeating calls. Given the simplicity of the tool, this is fully complete and leaves no significant ambiguity about its behavior or use case.

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 defines an empty object. The description compensates by explaining the output content in detail (platform description, credit prices, anonymity/reputation rules, discovery URLs). While there are no parameters to explain, the description adds meaning about what the tool provides, which is valuable. Baseline for 0 params is 4.

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's purpose: 'Explains what cogDepot is, what it costs, and where its machine-readable contracts live.' It uses a specific verb ('explains') and resource (cogDepot) and immediately distinguishes it from siblings by noting it should be called 'first when asked what cogDepot is, what it charges, or whether it fits a task.' This is unambiguous and separates it from cogdepot_get_started and cogdepot_preview_listings.

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 description provides explicit when-to-use guidance: 'Call this first when asked what cogDepot is, what it charges, or whether it fits a task.' It also warns against repeated calls ('Do NOT call it repeatedly - the answer only changes when cogDepot changes its pricing'). However, it does not name alternative sibling tools explicitly, only implies precedence with 'first.' This is clear context but lacks explicit exclusion of alternatives.

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

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

The description adds non-obvious behaviors not covered by annotations: requires no API key, spends no credits, returns instructions, and does not create accounts or send requests. These complement the readOnly and idempotent hints without contradiction.

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?

Every sentence delivers unique value: purpose, usage triggers, coverage, return behavior, and exclusions. Front-loaded with the core purpose, and no filler or redundancy.

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 explicitly states it returns instructions for a human/agent to follow. It also discloses the lack of side effects (no account creation, no requests), making the tool's context fully understandable.

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?

There are zero parameters; the tool's behavior is fully explained without needing parameter details. The description covers what the tool does and its scope (three ways to get a key), which suffices given no input parameters.

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's purpose: explaining how to obtain a cogDepot API key and become able to trade. It explicitly differentiates from siblings by defining when to call it (no account, missing/unfunded key) and what it does not do (create account, send requests).

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 (when user lacks account or key is missing/unfunded) and when-not-to-use (does not create account or send requests). It also names alternatives implicitly through context, making the guidance complete.

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

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.