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

With no annotations, the description carries the full behavioral burden. It discloses the return shape ("normalized items plus total/pages") and pagination ("page: pagination (1+)"), which is genuinely useful, but says nothing about permissions, rate limits, or whether the call is read-only.

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 purpose is front-loaded in the first sentence and the remaining parameter notes are terse with zero filler. The telegraphic style is efficient though slightly clipped at points.

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 6-parameter tool with no output schema and no annotations, the description covers the essentials: purpose, platform lookup, pagination, filter names, and return contents. It stops short of explaining what "worthy/normalized" content means, valid sort or category vocabularies beyond one example, or any safety profile.

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 0%, so the description must compensate, and it largely does: it explains page (1+), points platform at graze_platforms(), gives sort examples ("views", "recent"), and names category and min_views. It still leaves min_views and category semantics to inference, but the coverage is far better than the schema alone.

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 verb phrase "Search/discover worthy content matching `query`" states a concrete action and resource, so the tool's function is unambiguous. However, it gives no differentiation from siblings graze_trending or graze_feed, leaving the agent to guess which discovery surface applies.

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 notes that platform values come from graze_platforms(), which is a useful prerequisite, but it never states when to choose graze_discover over graze_trending or graze_feed. There are no exclusions or selection conditions, only parameter-level hints.

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?

With no annotations, the description carries the full behavioral burden. It usefully discloses that ranked=True uses a popularity ranker that includes an explanation and ranked=False returns newest, plus the limit bound of 1-50. It omits pagination behavior, default ordering, what the 'explanation' contains, and whether any auth is required.

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 and front-loaded, delivering the tool's identity first and then the parameter semantics with no filler. It is terse to the point of being fragmentary, but 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?

For a three-parameter tool with no annotations, no output schema, and 0% schema description coverage, the description should explain the platform parameter and the shape of what comes back. It covers the ranked and limit behavior but leaves a full third of the interface — and the return format — undocumented.

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 0%, so the description must compensate. It does well for two of three parameters — both branches of ranked and the 1-50 range of limit (the schema only shows a default) — but says nothing about the platform parameter or its 'bottube' default, leaving that third parameter fully opaque.

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 identifies the resource ('Discovery feed') and explains its two modes of operation via the ranked flag, which is more than a tautology. However, it never uses a distinct verb and does not differentiate the tool from close siblings like graze_discover or graze_trending, so an agent cannot confidently tell which feed tool to pick.

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 explicit when-to-use guidance and no mention of alternatives such as graze_discover or graze_trending. The ranked semantics imply a use case (popular vs chronological browsing) but the agent must infer when this feed is preferable to its siblings.

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?

With no annotations provided, the description carries the full behavioral burden. It does disclose that status information is included in the output, which is useful context. However, it says nothing about whether this is a read-only listing, any rate limits, or the shape of the status field.

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?

Single sentence, front-loaded with the verb and object, no wasted words. Appropriately sized for a no-parameter listing tool.

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 simple zero-param listing tool, this is close to adequate. But with no annotations and no output schema, the description should at least clarify what 'status' means or how the list relates to sibling discovery tools. It leaves a small gap an agent might need to resolve.

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?

Zero parameters, so baseline is 4. There are no parameters to describe and the description appropriately doesn't invent any.

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 ('content platforms grazer can discover across') with added scope ('with status'). It's clear what the tool returns, though it doesn't differentiate itself from siblings like graze_trending or graze_discover.

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?

No indication of when to use this tool versus graze_trending, graze_discover, or graze_feed. The description simply states what it returns without any routing context.

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?

No annotations and no output schema are provided, so the description carries the full burden: it says nothing about return shape, pagination, ordering of trending items, rate limits, or authentication. The only behavioral hint is the implicit read-only nature of 'Return'.

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 clauses with the core verb leading and parameter notes trailing; nothing is wasted. The telegraphic phrasing ('limit 1-50') is efficient but slightly clipped.

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 annotations, the description should say more about what trending content looks like when returned. The parameter guidance is adequate, but the return-value gap and absence of any behavioral context leave it only minimally complete for an agent calling it cold.

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 0%, so the description has to compensate, and it does useful work: it bounds 'limit' to 1-50 (the schema only shows a default of 10) and tells the agent where valid 'platform' values come from via graze_platforms(). It omits defaults and the platform string format, so it is not fully complete.

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 gives a specific verb and resource ('Return trending content') with a scoping qualifier ('on a platform'), so an agent can tell it fetches trending items rather than a feed or discovery results. It stops short of naming the sibling tools (graze_feed, graze_discover) to sharpen the distinction.

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 by the word 'trending'; there is no explicit statement of when to pick this over graze_feed or graze_discover. The 'see graze_platforms()' pointer is a parameter hint, not a usage guideline.

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