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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive behavior. The description adds value beyond those by specifying error behavior for malformed ids and removed listings. The only minor redundancy is restating 'read-only' when annotations already provide it.

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 compact, front-loaded with the core purpose, then delivers id format, behavior, errors, and exclusions in a logical order. Every sentence earns its place and none are wasted.

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 single-parameter tool with no output schema, the description is complete: it specifies the id format with examples, explains error cases, declares read-only behavior, and routes the agent away from the wrong sibling tool. Nothing essential 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 baseline is 3. The description adds further value by providing concrete id format examples ('facebook:12345' or 'ebay:v1|123|456') and by clarifying that ids from search_marketplace are not valid here. This goes beyond the schema's brief description.

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 states a specific verb and resource ('Fetch one listing in full') and immediately ties it to ids returned by the search tool. It also distinguishes itself from get_listing_details by explicitly saying what it is not for, so an agent can pick the correct tool without ambiguity.

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 clearly states when to use the tool: for ids returned by the search tool. It also gives an explicit exclusion and alternative: ids from search_marketplace should use get_listing_details instead. This is direct, actionable routing guidance.

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?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive behavior. The description adds valuable behavioral context beyond those: one listing per call, no login required, photo fetch/fallback behavior, and concrete error behavior for removed listings or wrong-marketplace IDs. This exceeds what annotations alone provide.

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 dense but well organized: the core purpose is front-loaded, the photo-mode behavior is explained in compact conditional terms, and the constraints/errors/not-for guidance are each one clear sentence. No sentence is wasted.

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?

Despite having no output schema, the description tells the agent what fields will appear, how photos behave in both modes, how to cap payload, what requirements apply, what errors look like, and what the tool is not for. This is complete enough for correct invocation and expectation-setting.

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 already 100%, and the description additionally explains the semantic difference between imageMode values, the automatic fallback from inline to URLs, the resolution tradeoff of imageSize, maxImages as a payload cap, and the includeImages alias. This adds substantial meaning beyond the schema definitions.

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 states a specific verb ('Get'), a specific resource ('one listing in full'), and the source of the ID ('search_marketplace or a marketplace URL'). It lists the returned content and explicitly distinguishes itself from searching and batch fetching, making it clearly different from its siblings.

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 gives explicit when-to-use guidance: retrieve one full listing by ID. It names alternatives for what it is not for — 'search_marketplace' for searching and no batch operation for many listings — and even notes the same requirements as search_marketplace apply.

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?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive behavior. The description adds useful behavioral context beyond annotations: 'read-only, no arguments, no network calls beyond a health check,' and specifies what information each marketplace entry includes. No contradiction with 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 four sentences, each earning its place: purpose, when to call, behavioral characteristics, and exclusions. It is front-loaded with the core listing purpose and avoids irrelevant detail.

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 read-only listing tool with no output schema, the description fully covers what the tool returns, when to call it, its behavioral constraints, and what it is not for. An agent has enough to select and invoke it correctly.

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 and 100% schema coverage, so there is no parameter ambiguity. The description reinforces this by explicitly stating 'no arguments,' which is sufficient for an agent to call the tool correctly.

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 uses a specific verb and resource: 'List the marketplaces this server can search right now', with concrete output details (display name, credential requirement, reachability). It explicitly differentiates from siblings by stating 'Not for: searching or fetching 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 gives explicit trigger conditions: 'Call it once when a search fails with an unknown-marketplace error or before offering a marketplace the user did not name.' It also names exclusions ('Not for: searching or fetching listings'), making alternative selection clear.

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?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds meaningful context beyond annotations: Facebook results use the server's default location due to the contract carrying no location, and results expose ids compatible with the fetch 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?

The description is front-loaded with the core purpose and is compact overall. Each clause adds useful routing or behavioral context, though the explicit 'Behavior: read-only' phrase is redundant with the readOnlyHint annotation.

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 there is no output schema, the description helpfully explains that results contain ids in marketplace:listingId form usable with the fetch tool. It also covers the main location caveat and exclusions, making it reasonably complete for a single-parameter search tool.

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% and the only parameter, query, is described as a search query string. The description adds little beyond restating that a single query string is used, so the baseline of 3 is appropriate.

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 verb and resource: search every available secondhand marketplace with a single query string. It also distinguishes itself from siblings by noting that search_marketplace is preferred when a location matters and that this tool is not for filtered or local searches.

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 explicitly provides when-to-use and when-not-to-use guidance: it says to prefer search_marketplace when a place matters and states that this tool is not for filtered or local searches. It also explains the downstream use case of passing returned ids to the fetch tool.

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?

Annotations already mark this as read-only and idempotent, and the description reinforces and extends that with concrete behavioral details: no login, no purchases, Facebook rate-limiting, 90-second caching, marketplace-specific credentials, and a defined error pattern. This goes well beyond what annotations alone 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?

The description is dense but well-ordered: purpose, marketplace requirements, behavior, errors, and exclusions. Every sentence carries operational value. One minor blemish is the incomplete "Marketplaces: ." fragment, which appears to be a formatting/placeholder artifact and adds no information.

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 17-parameter, multi-marketplace tool with no output schema, the description is remarkably complete. It specifies the return fields, marketplace-specific prerequisites, credential requirements, caching and rate-limit behavior, error handling, and clear exclusions. An agent has enough context to invoke the tool correctly and recover from common failures.

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 100%, so the baseline is 3. The description adds useful cross-parameter context beyond the schema, such as Facebook requiring "City, ST" location, eBay pagination behavior, price-bound tuning for empty results, and the distinction between thumbnails and full photos via get_listing_details. Some duplication exists, but the added meaning justifies a 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 uses a specific verb and resource: "Search live listings on secondhand marketplaces by keyword." It clearly distinguishes itself from get_listing_details by stating that details, photos, and shipping require a separate call, and it explicitly lists what it is not for.

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 gives explicit when-to-use and when-not-to-use guidance: it directs the agent to get_listing_details for richer item data, and it lists exclusions such as buying, messaging sellers, saved searches, and new-retail catalogs. It also provides practical guidance like widening keywords or dropping price bounds when results are empty.

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