Friction

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds one genuinely useful behavioral fact — that the per-category reports are a free *preview* and the full list lives behind the returned page/pricing links. It says nothing about what happens with an unknown slug or about limits on counts.

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?

A single sentence, front-loaded with the payload's core value ('what users struggle with') before the enumeration. It is dense and slightly overstuffed with parenthetical category lists and link caveats, but nearly every clause carries information the agent needs because there is no output schema.

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 annotations covering safety, the description must carry the return-shape burden and largely does: counts, problem areas, four report categories, source links, and page/pricing links. Only failure behavior for an unrecognized product slug is left unaddressed.

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 single `product` parameter already documents the accepted slug/name/domain format with an example (grafana). The description only says 'one product' and adds no further semantics, so the 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?

The description enumerates exactly what the tool returns for a single product: struggle counts, main problem areas, per-category preview reports (pain points, feature requests, workarounds, switching reasons) and links. That makes the resource and content unmistakable. It never explicitly contrasts itself with list_products or search_items, so it stops short of a 5.

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 only implied: the tool is a per-product overview with free-preview categories plus links to the full list. There is no statement of when to reach for this versus list_products (enumerate products) or search_items (find specific items), and no prerequisites or exclusions are given.

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 establish that this is a read-only, idempotent, non-destructive, closed-world operation, so the safety profile is covered. The description adds genuinely new behavioral context beyond that: default ordering is most-documented first, and each result carries report, recurring-theme and source counts. It omits pagination behavior, which is one gap.

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 sentences, no filler, and the returned data and ordering are front-loaded before the optional filters. Every clause carries 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, so the description correctly carries the return-shape burden by naming the counts returned, and the filters are covered. Pagination and total-count behavior are left to the schema, which is acceptable for a simple list 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%, so the parameters and their defaults are already documented in the schema. The description restates the filter semantics (category slug, name or domain fragment) without adding syntax or matching behavior beyond what the schema provides. 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 (List) and resource (software products with a page on Friction), plus scope qualifiers: documented-first ordering and the aggregate counts returned. An agent can tell this apart from get_product_summary, which returns a single product's summary, and from search_items, which searches items rather than products.

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 the browse/discovery use case through the sort order and filters, but never states when to choose this over get_product_summary or search_items, and gives no exclusions. Usage must be inferred from the resource name.

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 read-only, idempotent, non-destructive and closed-world behavior, so the safety profile is covered. The description adds genuine beyond-schema context: results are limited to free-preview reports, and each report exposes source threads with URL, date, quoted excerpt and state. It stops short of saying anything about result volume, ordering, or empty-result behavior.

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 sentences, no filler, and the primary scope (one product's free-preview reports) is front-loaded before the optional filters and the return-shape note. Every clause carries information an agent needs.

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 spends its second sentence describing what a report contains, which is the main information gap. What remains unaddressed is how many reports come back and whether ordering or paging applies, a minor but real omission for a 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 coverage is 100%, so baseline would be 3, but the description contributes real semantics the schema lacks: the query is conjunctive ('all words must match') and the searchable fields are the title and summary. It also makes explicit that product scopes the search to a single product.

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 ('Search the free-preview feedback reports of one product') plus the optional narrowing dimensions, which cleanly separates it from list_products and get_product_summary. An agent can tell from the description alone that this is the text/filter search entry point, not a listing or aggregate tool.

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 by noting the filters are optional and that all query words must match, but it never says when to reach for this versus the sibling listing/summary tools, nor when a category filter is preferable to a keyword query. The 'free-preview' qualifier hints at a scope restriction without stating what that means for the caller.

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