Friction

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful context beyond that: the result is a 'free-preview' subset with source links plus page/pricing links for the full list, which signals partial/limited output rather than a complete dataset.

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 dense sentence with the core purpose front-loaded and the parenthetical enumerations kept tight. No filler or restatement of the title.

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 must describe the return payload, and it does so thoroughly (counts, categories, source links, full-list links). The only gap is behavior for missing/invalid products and the exact scope of the 'free preview' limit.

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?

With one parameter at 100% schema description coverage (slug, name or domain, e.g. 'grafana'), the schema already carries the semantics. The description adds nothing about the product argument (e.g. matching behavior or unknown-slug handling), 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 uses a clear verb+resource framing and specifies exactly what the summary contains (counts, problem areas, per-category free-preview items, links). It is easy to distinguish in substance from list_products/search_items, but it never explicitly names or contrasts those siblings, so it falls 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?

There is no when-to-use statement, no prerequisites, and no reference to alternatives. The content list implies the tool is for retrieving an aggregated per-product view, but the agent is left to infer that against list_products and search_items on its own.

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 and idempotent behavior, so the description doesn't need to repeat safety. It adds useful details: ordering ('most-documented first') and what data is returned ('counts of reports, themes and sources'), which go beyond the 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?

Two sentences, front-loaded with the core action and then the optional filters. No wasted words.

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 read-only list tool with no output schema, the description provides enough to understand what will be returned (collections with counts) and how to filter. It doesn't describe pagination behavior beyond the schema, but that's covered by the 'limit' and 'offset' parameters.

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 schema has full coverage, so the parameters are well-documented. The description adds the concept of 'name or domain fragment' for the 'q' parameter, clarifying that it searches both fields, which is extra semantic value.

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 ('List') and resource ('software products that have a page on Friction'), clearly distinguishing it from siblings like get_product_summary (single product) and search_items (items). It also specifies ordering and what counts are included.

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 context—listing a catalog of products with optional filters—which is distinct from fetching a single summary or searching items. It doesn't explicitly state when to use it versus alternatives or mention exclusions.

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 readOnly/idempotent/non-destructive/non-openWorld, so the safety profile is covered. The description adds real behavioral context beyond that: results are limited to free-preview items and each item carries its source threads (URL, date, quoted excerpt, state), which is meaningful for a tool with no output schema.

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 tightly packed sentences with zero filler; the core scope and filters come first, with the result-content note following. Nothing restates the name or title.

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 usefully previews the return shape (items plus source threads), and all three params are accounted for. It is slightly thin on ordering/result-volume behavior, which an agent might want 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 the baseline is 3, but the description adds genuine semantics the schema lacks: 'q' requires all words to match (AND semantics, not OR or fuzzy), and the search is confined to one product rather than across products.

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 precise verb ('Search'), resource ('free-preview feedback items'), and scope ('of one product') plus the optional narrowing axes. The verb and the 'free-preview' qualifier make it unmistakably distinct from the sibling list_products and get_product_summary tools.

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 spelling out which filters exist (category, title/summary words) and the 'all words must match' condition, but it never says when to reach for this tool versus list_products or get_product_summary, and there are no exclusions or prerequisites.

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