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

With no annotations, the description carries the full burden of behavioral disclosure. It explains that resolution aggregates into UTC-aligned buckets with avg/min/max/count, summary collapses the whole range, top_n filters and sorts buckets, and the result includes total_buckets. This goes well beyond a simple 'fetch' statement, though it does not fully specify the response structure.

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 efficiently organized: a one-sentence purpose statement followed by compact, scannable sections for each option. Every sentence adds operational value and there is no filler. Parameter names are consistently formatted, aiding quick reference.

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 tool with 11 parameters and no output schema, the description covers the important invocation logic and combination constraints (summary vs resolution, top_n requiring resolution, order/top_by semantics). It even mentions the total_buckets field in the result. The only notable gap is that the exact return format is not described, though the aggregation semantics make it largely inferable.

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 defines start/end input formats (unix timestamp or rrdtool strings), resolution, summary, top_n, order, and top_by semantics with examples and constraints. However, the identifiers group, host, and plugin are not explicitly explained, leaving some parameters to be inferred from domain knowledge.

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?

Description opens with 'Fetch time series data for a single field,' a specific verb and resource that clearly differentiates it from siblings like list_hosts or get_metadata. The 'single field' qualifier adds precision about what data is returned.

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 strong conditional guidance for parameters ('use this for long time ranges to avoid returning hundreds of raw points', 'Cannot be combined with resolution'), but it does not explicitly say when to use fetch_series versus sibling tools such as render_graph or get_metadata. The usage context is mostly implied rather than stated.

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 burden of disclosing behavior. It clearly implies a read-only operation and explains the optional field-scoping behavior, but it does not describe what metadata is returned, how errors are handled, or how output is structured.

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 one tightly written sentence with no filler. The primary action is front-loaded, and the optional field behavior is integrated clearly without burrying the core purpose.

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?

The description is too sparse for a tool with no output schema, no annotations, and 0% schema description coverage. It omits the meaning of required parameters `group` and `host`, does not describe the return value, and gives no indication of how this relates to sibling tools like list_fields or fetch_series.

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 explains that `field` selects a single field within the plugin and implies `plugin` is the metadata target, but it says nothing about the required `group` and `host` parameters, leaving an agent without enough context to populate them 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 states a clear verb and resource: get metadata for a plugin, with a conditional for a single field. It is specific enough to distinguish the main action from siblings like render_graph and fetch_series, though it does not explicitly differentiate itself from list_plugins or list_fields.

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 guidance is given about when to prefer this tool over alternatives. The conditional 'if `field` is given' describes behavior, not selection criteria, and there is no mention of situations where list_fields or list_plugins would be more appropriate.

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?

There are no annotations, so the description carries the full burden of behavioral disclosure. 'List' implies a read-only operation, but the description does not clarify whether group/host are used for scoping or authentication, whether results are limited, or whether the operation has any side effects. This is minimal transparency beyond the operation name.

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 a single front-loaded sentence with no filler or repetition. It is concise and to the point, though its brevity contributes to the lack of contextual detail elsewhere.

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 tool with three required parameters, no schema descriptions, and no annotations, this description is too sparse to be complete. The output schema may cover return values, but the roles of host/group, the selection conditions, and behavioral expectations are all 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 coverage is 0%, so the description must compensate for the undocumented parameters. It adds meaning only to 'plugin' by identifying it as the thing whose fields are being listed; 'host' and 'group' remain semantically unexplained. This does not adequately compensate for the low schema coverage.

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 phrase 'List fields for a given plugin' names a specific operation and resource, and it is reasonably distinguishable from sibling tools like list_plugins and list_hosts. However, it does not explain why 'group' and 'host' are also required, leaving the exact scope of the tool partially underspecified.

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 no guidance about when to use this tool instead of siblings such as render_graph, get_metadata, or fetch_series. No prerequisites, exclusions, or selection conditions are provided, so the agent is left to infer usage from the tool name alone.

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 transparency burden. 'List all' signals a read-only, exhaustive enumeration, and 'discovered from the Munin datafile' clarifies the data source. It does not mention caveats like missing datafiles or performance, but the read-only nature is clear.

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 a single, front-loaded sentence with no redundant wording. Every word adds information: the operation, the output shape, and the data source.

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?

This is a simple parameterless enumeration tool with an output schema available. The description names the exact result and source, which is sufficient for an agent to select and invoke it correctly. No additional prerequisites or alternatives are necessary for this straightforward operation.

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 the schema is empty, so there is no parameter detail for the description to add. The description appropriately focuses on what the tool returns rather than 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?

The description clearly identifies the action ('List'), the resource ('(group, host) pairs'), and the data source ('Munin datafile'). It differentiates from siblings like list_plugins and list_fields by naming the specific pair type, though it does not explicitly call out 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?

The usage context is implied: use this tool when you need all discovered group-host pairs from the Munin datafile. However, it provides no explicit guidance about when not to use it or which sibling tool to prefer for other listing needs.

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 are provided, so the description carries the full burden. 'List' signals a read-only operation, which is transparent, but there is no detail about side effects, permissions, failure behavior, or how the host/group scope is interpreted.

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 a single, front-loaded sentence with no filler words. It efficiently states the core operation and scope.

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?

The tool is simple and has an output schema, so return details are covered elsewhere. However, the description omits the role of the required 'group' parameter and gives no usage routing guidance, leaving moderate gaps for an agent.

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 clarifies that host is the target of the listing, but says nothing about 'group' or how host and group relate, leaving a required parameter semantically unexplained.

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'), a resource ('plugins'), and a scope ('for a given host'). It distinguishes itself from siblings like list_hosts and list_fields, though what 'plugins' means precisely is left vague.

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 guidance is given about when to use this tool versus alternatives such as render_graph, list_hosts, or fetch_series. The description implies a use case but provides no explicit context, exclusion, or selection condition.

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 burden of behavioral disclosure. It states the output is a PNG graph but does not mention side effects, required permissions, behavior with invalid fields, time-range handling, or whether the operation is read-only. The description lacks the added context needed to understand the tool's runtime 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?

The description is a single, front-loaded sentence with no wasted words. It states the action, output format, and data source efficiently. Every part earns its place.

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 an 8-parameter, 6-required tool with no annotations and no output schema, a single-sentence description is insufficient. It doesn't explain what 'start' and 'end' refer to, what values 'group' and 'host' expect, or how fields are specified. An agent would need to guess at most of the required inputs.

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 identifies 'fields' and 'plugin' as the data to plot, but says nothing about 'group', 'host', 'start', 'end', 'width', or 'height'. The description adds minimal meaning beyond the schema's parameter names and leaves several parameters ambiguous.

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 ('Render') and a concrete resource ('PNG graph'), and mentions the data source ('given fields of a plugin'). This makes the tool's role clear and differentiates it from sibling listing/fetch tools, though it doesn't explicitly name a sibling. It stops short of a 5 because it does not draw an explicit contrast with related tools like fetch_series.

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 guidance about when to use this tool versus alternatives such as fetch_series or list_fields. No prerequisites, constraints, or exclusions are stated. The only usage signal is the inherent purpose implied by the verb, which is not enough to qualify as explicit guidelines.

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