EcomPick

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

Annotations already cover safety (readOnly, idempotent, non-destructive, openWorld), so the description's added value is in disclosure of output behavior: it includes sources and last-checked dates, and explicitly makes no scores or invented prices. That is a meaningful honesty/uncertainty contract an agent would not get from annotations alone.

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?

Two dense sentences: what is compared and along which dimensions first, then the output-integrity guarantee. No filler, no restatement of the tool name.

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 a single fully documented parameter and no output schema, the description carries the return-value burden and does so partly, naming sources, last-checked dates and the absence of scores/prices. It does not say what happens with an unknown or unpublished slug, a minor but real gap.

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 schema already documents the slugs array, its 2-3 item bounds, uniqueness and the 'exact slug from search_tools' example. The description only echoes the 'two or three distinct' constraint; it adds no format or sourcing detail beyond the schema. Baseline 3 applies.

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 verb (compare) and resource (two or three distinct published tools) plus the exact comparison dimensions: pricing label, official pricing page, platforms, any-store support, delivery kind. This clearly separates it from single-tool siblings like get_tool, though no sibling is named explicitly.

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 constraint 'two or three distinct published tools' implies the use case (side-by-side evaluation of published entries), but there is no explicit when-to-use/when-not guidance and no routing to get_tool or find_alternatives for the single-tool or discovery cases.

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, idempotentHint, destructiveHint=false and openWorldHint, so safety is covered. The description still adds real behavioral value by disclosing the empty-list outcome when no alternatives are documented and explicitly stating it will not fabricate substitutes, which prevents an agent from misreading an empty result as an error.

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?

Two short sentences with no filler, and the core purpose is front-loaded ahead of the edge-case behavior. Every clause carries information the agent cannot get from the name alone.

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 read-only lookup with full schema coverage and annotations, the description covers the essential contract, including the empty-result case. The main remaining gap is that it does not characterize the shape of a non-empty result (e.g. names or links), though with no output schema this is a minor omission.

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 is a single required parameter at 100% schema description coverage, and the schema already explains that 'slug' is the exact tool slug from search_tools with a concrete example. The description adds nothing further about the parameter, so the baseline 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 names a specific verb ('Get') and a precise resource ('editorially linked published alternatives to a tool'), which is more specific than a generic 'find similar tools'. It does not explicitly contrast itself with the sibling compare_tools, but the qualifier 'editorially linked published' narrows the scope enough that an agent can distinguish it from a generic search or comparison.

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?

Usage is implied by the purpose: call this when you need documented alternatives for a known tool. The line 'does not guess substitutes' gives useful negative guidance, but the description never names an alternative tool (compare_tools, get_tool) or states the condition that would route an agent to one of them instead.

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, idempotentHint and destructiveHint=false, so the agent knows the safety profile. The description adds a useful trust signal ('Does not invent prices or ratings'), indicating data is sourced rather than generated, but says nothing about behavior for a nonexistent slug or the response shape.

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?

Two short sentences: the operation and its return payload come first, followed by one clarifying caveat about data fidelity. Nothing is redundant or padded.

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 correctly carries the burden by listing the returned fields, which is the key missing structured information. The only gap is unspecified behavior for unknown slugs or tools not yet published.

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% and includes a concrete example, so the baseline is 3. The description still adds value by stressing 'exact slug', implying strict, non-fuzzy matching — a semantic detail the schema does not convey.

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 verb and resource ('Get one published tool by exact slug') and immediately enumerates the fields returned (tagline, pricing label, alternatives, source, last checked date). This clearly distinguishes it from search_tools, which returns many tools rather than one.

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 'by exact slug' constraint establishes the usage context: this is a follow-up lookup once a slug is known, reinforced by the schema note 'Exact tool slug from search_tools'. However, the description itself never names search_tools or compare_tools as alternatives or states when not to use it, leaving that inference to the reader.

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 cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the description's job is to add substance — and it does, disclosing the inclusion rule ('explicit platform support, excluding tools marked only as any-store') and the freshness caveat of oldest last-checked dates. The odd mention of 'counts' alongside 'IDs and names' leaves the return shape slightly muddled, keeping it off a 5.

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?

Three short sentences with the core purpose front-loaded, so the agent gets the point immediately. The trailing sentence packs several loosely related facts (counts, source links, last-checked dates) that read as a compressed return-value dump rather than a clean statement.

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 parameters and no output schema, the description carries the burden of explaining what comes back, and it does name the fields returned. Those field names ('counts', 'oldest available last checked dates') are described opaquely enough that an agent still can't fully predict the payload shape.

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, which is the baseline-4 case: there is nothing for the description to disambiguate, and it correctly signals a no-argument enumeration.

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 verb and resource — 'List commerce platform IDs and names' — and scopes it to feeding the platform filter, which clearly separates it from tool-search siblings like search_tools or get_tool. It never names an alternative, but the distinct resource makes the distinction unambiguous.

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 phrase 'for the platform filter' implies when an agent would want this list, but there is no explicit when-to-use guidance, no statement of what to do with the result, and no mention of alternatives or prerequisites.

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 readOnly, idempotent, open-world and non-destructive, so safety is covered. The description adds useful payload context (counts, links, an aggregated oldest date), but says nothing about result ordering, pagination, or size, which matters for an open-world list 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?

One sentence, front-loaded with the primary content (task IDs and names) followed by the ancillary fields. The trailing list of fields makes it dense but every element conveys real 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?

With no output schema and no parameters, the description carries the burden of describing return shape and does so by naming the fields returned. Minor gaps remain around the meaning of 'oldest available last checked date' and the ordering of results.

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, so there is no parameter semantics to explain; the baseline of 4 applies. The description correctly implies a single unfiltered call with no arguments.

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 verb+resource (list seller task IDs and names) and enumerates the fields returned: published tool counts, EcomPick links, oldest last checked date. It does not differentiate from the closest sibling, list_platforms, and the qualifier 'for the task filter' is ambiguous without further explanation.

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?

There is no statement of when to use this tool versus search_tools, list_platforms, or get_tool. The phrase 'for the task filter' hints at a use case but never spells out an alternative or an exclusion.

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, idempotentHint and openWorldHint, so the safety profile is covered. The description adds genuinely new behavioral context: a 20-result cap, inclusion of source links and last-checked dates, AND semantics across filters, and the caveat that any-store tools are not implied to have native integrations. It stops short of describing result ordering or what happens when no filters are supplied.

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?

Three sentences, zero filler, front-loaded with purpose, then behavioral detail, then the one caveat an agent could otherwise misread. Every sentence carries distinct 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?

There is no output schema, yet the description covers the return shape (up to 20 concise matches, source links, last checked dates) and a semantic caveat about result interpretation. Combined with six fully documented parameters and a read-only annotation set, an agent has everything needed to call and interpret this 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 coverage is 100%, so the baseline is 3; the description goes beyond it by stating that filters combine with AND, which is parameter interaction the schema does not express. It does not clarify that all six parameters are optional or what an unfiltered call returns, so it is not exhaustive.

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 verb (find) and resource (published ecommerce tools) and enumerates the filterable dimensions, so the agent knows exactly what corpus it queries. It is clearly a multi-result search rather than a single-record lookup, but it never names the sibling it is not (e.g. get_tool or compare_tools), so differentiation is inferred from scope rather than stated.

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 implies usage via the filter list and the 'filters combine with AND' note, which tells the agent how to compose a query, but there is no explicit when-to-use/when-not guidance or named alternative for single-tool or comparison needs. The any-store caveat is useful but is about result interpretation, not tool selection.

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