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

The description says the tool "stops a running query" while annotations declare readOnlyHint=true, implying no state change. That is inconsistent: cancellation is a state mutation. The added note about partial results remaining readable is useful, but the core safety profile is contradictory.

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 tight sentences with the action front-loaded and the retention behavior following. Every sentence carries information, though a routing hint would improve it.

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-parameter tool with no output schema, explaining the retention and expiration of partial results is good context. But the undocumented resultId and the annotation contradiction leave real 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?

One required parameter (resultId) has 0% schema description coverage, and the description never explains what a resultId is or where to obtain it. The description adds no meaning beyond the parameter name at all.

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: "Stops a running query." An agent can grasp the action immediately. It does not, however, differentiate itself from siblings like get_result or read_result, which handle query output.

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 on when to cancel versus using get_result/read_result, no mention of prerequisites such as needing an active query or a valid resultId, and no note on what happens after cancellation (e.g., how to fetch remaining results).

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 cover readOnly, idempotent, non-destructive, and closed-world, so the safety profile is known. The description adds genuinely useful behavior beyond that: drill-down is hierarchical/stepwise and schemas are 'sampled' rather than exhaustive, which affects how the agent should interpret results.

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 dense sentences with the core action front-loaded and the operational hint second. The parenthetical source-type list is long but earns its place by clarifying breadth; nothing is redundant.

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 read-only discovery tool with no output schema, the definition conveys enough: what it enumerates, how to drill down, and that schemas are sampled. Minor gap in not describing the shape of returned results, but that is largely inferable from the enumerated metadata kinds.

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 'path', 'filter', and 'source' are already documented with examples and wildcard syntax in the schema itself. The description restates the drill-down and wildcard concepts without adding format or semantics beyond that baseline.

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 (browses) and resource (metadata of a source) and enumerates the concrete metadata kinds it can return across source types. It doesn't explicitly differentiate itself from siblings like query or list_sources, though the exploratory 'step by step' framing implies discovery rather than querying.

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?

'Use path to drill down and filter ... to narrow' explains how to operate the tool but not when to choose it over query, list_sources, or read_result. Usage is implied as an exploratory/discovery step, but no explicit when/when-not or alternative routing is 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 cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds genuinely non-obvious context: downloads resolve through a single manifest URL and all files are listed in that manifest. It does not describe the status values or what happens on repeated polling, but that gap is smaller given the annotation coverage.

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 with no filler, and the payload summary is front-loaded ahead of the wait hint. The first sentence is a compressed noun list rather than a statement of action, which costs a little readability but no space.

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 carries the full return-value burden and does so well, covering status, progress, counts, limits and download mechanics. The remaining gaps—resultId provenance and the possible status values—are meaningful for a polling tool but not fatal.

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 description's wait clause restates the schema verbatim ('Seconds to wait for a status change', max 10) and adds no semantics. resultId, the required parameter, is undocumented in both the schema and the description, so the agent has no hint about where a resultId comes from.

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 result: status, progress, schema, row counts, window limits and download info, so an agent knows the resource and payload. It stops short of naming the sibling read_result, so there is no explicit differentiation between polling metadata and fetching actual data.

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 guidance is 'Use wait (seconds, max 10) to wait for a status change', which repeats the schema constraint rather than explaining when to poll versus calling read_result or list_sources. There are no exclusions or alternatives named, so tool selection is left entirely to inference.

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 readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description adds real context beyond that by naming what is returned, including dialect hints, limits and active read-only layers, which tells the agent what it can learn before querying.

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?

One sentence, front-loaded with the verb, followed by an enumerated payload list. Slightly list-heavy but every item conveys what the agent can extract.

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 parameters, no output schema and fully covered annotations, the description carries the remaining burden and does so by describing the returned content. Minor gaps: no mention of ordering, permissions or whether results are scoped to the caller's workspace.

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 takes zero parameters, so the baseline is 4; the description correctly implies no filtering arguments are needed.

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 ('Lists the data sources you may query') and enumerates the fields returned, which makes it distinguishable from query/get_result. It does not explicitly contrast itself with the sibling 'describe', but the discovery framing is clear.

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?

'you may query' hints that this is a pre-query discovery step, but there is no explicit when-to-use or when-not-to-use guidance, and no routing against the sibling 'describe' tool.

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=true and destructiveHint=false, yet the description still adds real value: the call returns immediately with a resultId rather than results, and invalid/non-read-only queries fail fast with a rejection reason. Missing detail on size limits or timeouts, but the async-vs-sync behavior is the critical disclosure and it is present.

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?

Three tight sentences with the return behavior front-loaded, then the language dependency, then the follow-up call. No filler and no repetition 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?

With no output schema, the description correctly supplies the return value (resultId) and the continuation path, which is the main thing an agent needs. It could say more about result lifetimes or options, but for a 4-parameter read-only launcher this is close to complete.

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 schema even enumerates the query dialects, so the baseline is 3. The description's only added semantics is that the applicable language is determined by the chosen source via list_sources, which is useful but marginal; nothing is said about `params` or `options` formats beyond the schema.

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 (starts a read-only query) plus the exact return contract (a resultId, immediately), which signals the async pattern. It also distinguishes itself from the follow-up siblings get_result/read_result by naming them as the next step.

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?

Gives clear context: query language depends on the source (see list_sources), and the agent is told to follow up with get_result/read_result. It stops short of stating when NOT to use this tool (e.g. re-reading an existing resultId, or cancelling via cancel_query), so it is strong but not fully routing-aware.

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 cover the read-only/idempotent/non-destructive profile, yet the description still adds non-obvious behavior: values are truncated when read inline but complete in downloads, and the returned payload shape depends on the result kind. It stops short of describing pagination boundaries or what happens past the end of a window.

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 front-loaded sentence with the general case first, then the mode-specific exceptions, then the truncation caveat. Dense but every clause carries information; slightly cramped to read in one pass.

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 7-parameter, no-output-schema read tool, the description covers both result modes, the column selection option, and the truncation tradeoff — enough to invoke correctly. Gaps are minor: no hint about where resultId originates or what an out-of-range window returns.

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 only 29%, so the description carries real weight — it maps offset/limit/columns to the row mode and file/lineOffset/lineLimit to the blob text mode, and clarifies that 'file' comes from a listing row. The one required parameter, resultId, gets no explanation in either place.

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 ('Returns one window of a result inline') and immediately distinguishes the two payload shapes: tabular rows vs. blob files/images. It does not name a sibling tool, so an agent must infer the boundary with get_result and describe on its own.

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 implied by the mode enumeration — use offset/limit for row results, file + line range for blob text, file alone for images — and 'downloads keep full values' hints at when to prefer a download instead. However, no alternative tool is named and there is no explicit 'use this when' statement.

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