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

Annotations already declare read-only, open-world, non-destructive behavior. The description adds meaningful operational context: the target URL, public/no-bearer auth, and the Accept header. It stops short of describing rate limits or what the main actions 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?

The description is compact and front-loads the toolset and actions. It could be tightened by grouping the transport/auth details together and by placing the help/target behavior closer to the action list, but there is little wasted text.

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?

It covers auth, endpoint, and action inventory, which is solid for a read-only meta tool. However, without an output schema, the description does not explain what healthcheck or latest return, leaving an agent to infer the main action semantics.

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 input schema already documents action, target, body, query, and params. The description's note that help with target returns an action's parameters restates the schema rather than adding new per-action parameter requirements.

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 the meta toolset, lists the concrete actions healthcheck and latest, and explains the help action. It lets an agent distinguish this from the results/servers/stats siblings at a high level, though 'meta toolset' could be more explicit about what each action returns.

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 when-to-use guidance is given: it does not say when to pick healthcheck versus latest, or when this meta tool should be chosen over results, servers, or stats. The only procedural note is how help with target behaves.

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, non-destructive, openWorld, so the safety profile is covered; the description adds genuinely non-obvious operational context: the target server comes from SPEEDTEST_TRACKER_URL, requests carry a Bearer token, and the caller needs the results:read ability. It does not describe result shape, pagination, or ordering for `latest`, but the auth/environment disclosure is real value 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?

The opening sentence front-loads the scope and the action list is kept to the end. The middle sentences are telegraphic ("Authenticated routes send Authorization Bearer", "Required abilities: results:read") but each carries distinct operational information, so there is little waste.

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 five-parameter tool with nested objects and no output schema, the definition covers transport, auth, and the action set, but leaves gaps around what each action returns, which query/params keys apply to which action, and whether list is paginated. An agent could invoke it, but would likely need to call `help` to use it correctly.

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 action, target, query, params, and body are already documented in structured form. The description only restates the help+target behavior, adding no syntax, expected keys per action, or examples 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?

The description names the resource domain ("results toolset") and enumerates the concrete operations ("list, get, latest"), which lets an agent separate it from the meta/servers/stats siblings. It never states what a "result" actually is (a recorded speedtest measurement), so the resource noun stays somewhat abstract.

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 only usage guidance is the mechanical note that "action help with target returns one action's parameters." There is no explanation of when to use list vs get vs latest, no prerequisites, and no pointer to which sibling tool to prefer for adjacent data.

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?

Beyond the annotations (which already mark it read-only, non-destructive, and open-world), the description adds concrete operational context: the SPEEDTEST_TRACKER_URL target, Bearer auth on authenticated routes, the required 'ookla:list-servers' ability, and the Accept header. It does not discuss rate limits or response shape, but the auth/ability constraints are genuinely useful.

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?

It is compact and all sentences carry information, but the opening 'covers the servers toolset (1 operations)' is meta boilerplate, and the fragmented header-style sentence sequence ('Every request sends Accept: application/json.') is less front-loaded than a single clear purpose sentence would be.

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 five-parameter gateway tool with nested objects and no output schema, the description covers auth, routing, and the help action, but it does not explain what the list action returns or which query/params fields are meaningful for listing servers. Adequate but incomplete for the tool's complexity.

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 schema already documents action, target, body, query, and params. The description only clarifies the help/target interaction and the enum values for action, adding little beyond the schema; 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?

It states the tool covers the 'servers toolset' with a single action 'list' and a required ability 'ookla:list-servers', which implies listing speedtest servers. But the wording is meta/framework-oriented ('covers the servers toolset (1 operations)') rather than a clean verb+resource statement, and it does not clearly distinguish it from the sibling results/stats/meta 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 only usage guidance is 'action help with target returns one action's parameters', which explains the help action but not when to use this tool rather than speedtest_tracker_results or speedtest_tracker_stats. No alternatives or when-not-to-use conditions 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?

Beyond the read-only, non-destructive annotations, it discloses the `SPEEDTEST_TRACKER_URL` destination, bearer authorization on authenticated routes, the required `results:read` ability, and the JSON Accept header. It does not explain aggregation scope or response behavior, but these are concrete operational details rather than repetition of 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?

The description is compact and front-loads the toolset scope before covering connection, authentication, discovery, and available actions. Telegraphic phrasing, the grammatical error `1 operations`, and some repetition of schema-visible information keep it from being excellent.

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-operation tool with a fully described schema, the authentication details and help mechanism make it minimally usable. With no output schema, however, the lack of any explanation of what `aggregated` returns or accepts leaves the agent dependent on discovery calls and unable to confidently distinguish it from the results sibling.

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 baseline is 3. The help-and-target explanation adds a little behavioral context, but largely duplicates the schema and provides no additional semantics for `body`, `query`, or `params` when invoking `aggregated`.

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 Speedtest Tracker stats toolset and its sole `aggregated` action, but never states with a clear verb what that action retrieves or calculates. The distinction between aggregated stats and the sibling `speedtest_tracker_results` tool is left to inference.

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?

It provides useful invocation guidance by explaining that `action` set to `help` with `target` returns an action's parameters, and it enumerates `aggregated` as the available operation. It gives no explicit when-to-use guidance or sibling alternatives for choosing between stats, results, servers, and meta.

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