KeepBal

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the bar is lower, and the description still adds real context: no new execution or polling fee, a possible settlement of the original charge, and that REST ownership/access controls apply. That cost and access-control disclosure is exactly the kind of thing annotations cannot convey.

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 short sentences, all load-bearing: purpose, cost/ownership caveat, and trigger. Front-loaded with the action and resource; the only mild drag is the vague phrase "through REST ownership and access controls."

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 read/settle tool with no output schema and rich annotations, the description covers purpose, trigger, cost, and access prerequisites. The main omission is any hint of what the response contains (e.g., run status), though no output schema exists to lean on.

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% for the single run_id parameter, so the schema contributes nothing. The description references run_id and implies its provenance (obtained from run_tool's pending result), which is modest value, but it gives no format, length, or lookup guidance.

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 specific verb pair (check/settle) and resource (an existing run) keyed by run_id, which clearly separates it from run_tool's execution-starting role. The term "settle" is domain jargon that an agent must infer means finalizing status/billing rather than mutating the run, which keeps it 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?

"Use after run_tool reports pending" gives an explicit trigger and names the sibling tool that precedes it, which is strong routing guidance. It does not state when NOT to use it (e.g., after a run completes or fails), so it stops short of full when/when-not coverage.

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, non-destructive, idempotent and closed-world; the description adds real value on top by confirming no provider contact/no cost and disclosing that unknown schemas are marked rather than silently omitted. It stops short of describing return structure for known tools.

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 short, front-loaded sentences with zero filler; the core read action comes first, then the cost/safety note, then the edge-case behavior.

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 enumerates the returned content (metadata, parameters, pricing, JSON example) and flags the unknown-schema case. Only the tool-identifier format and any size/rate limits are unaddressed, which is minor for a one-parameter read.

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 'tool' parameter with 0% schema description coverage, yet the description never says how a tool is identified (name, id, slug) or how unknown tools are handled. 'Unknown input schemas are explicitly marked' hints at output rather than input semantics.

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+resource: reading local tool metadata (parameters, pricing, request example). The word 'local' plus 'does not contact a provider' implicitly separates it from run_tool, though no sibling is named explicitly.

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?

'Free; does not contact a provider' implies inspection-before-execution usage, but there is no explicit when-to-use vs search_tools/get_run/run_tool guidance or exclusion statement. Usage is inferable 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?

Annotations only state the safety profile (destructive=true, idempotent=false, openWorld=true); the description adds the economics and lifecycle that annotations cannot express: successful calls are charged, provider failures are not, pending runs poll for up to 25 seconds, and truncated results must not be retried. Nothing here contradicts the destructive/non-idempotent hints — the no-retry rule reinforces them.

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?

Six short sentences, each carrying a rule (cost, failure billing, polling window, retry ban) and front-loaded with the core action. The opening 'using the REST billing and access controls' and the trailing 'Models use their documented REST endpoint' are boilerplate/unclear enough to cost a point, but there is no padding.

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 no-output-schema, open-world execution wrapper, the description covers cost model, failure charging, polling window, fallback tool, and retry prohibition — the operational facts an agent needs. What is missing is any notion of what the target tool's input should look like or what a returned run result contains (status, output, id), which the agent must guess.

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% for both required parameters, so the description must carry the burden and it does not: it never states the format of 'tool' (name? slug? namespaced id?) nor the shape of the free-form 'input' object passed to the target tool. The line 'Models use their documented REST endpoint' gestures at input semantics but is too vague to be actionable.

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?

Starts with a concrete verb+resource pair ('Execute a public tool') and immediately frames the billing/access model, which is the distinguishing trait versus siblings get_run, inspect_tool and search_tools. It explicitly routes the agent: 'Inspect first' (inspect_tool) and 'use get_run to check later' (get_run). An agent can pick this tool apart from its siblings without opening a schema.

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 an explicit ordering rule ('Inspect first'), an explicit alternative for polling ('use get_run … without starting another execution'), and a hard when-not-to condition ('Truncated or unsupported results must not be retried'). This is close to a full when/when-not/alternative matrix.

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 and non-open-world behavior, so the bar is low; the description still adds real context by noting the search is run 'locally, free of charge' and that results are ranked and paginated. It stops short of describing result shape or pagination mechanics, but it meaningfully enriches the annotation picture.

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 short front-loaded sentences with no padding, which is structurally sound. However, the character-count sentence duplicates schema constraints and the category sentence is awkward enough to obscure rather than clarify, so not every sentence fully 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?

With no output schema and 0% parameter coverage, the description should explain the four inputs and return behavior; it covers query length and vaguely mentions ranking and pagination but leaves limit, offset and category unexplained. Annotations fully carry the safety profile, so the gap is confined to parameter guidance.

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% across four parameters, so the description must carry the load. It restates the 2–200 character query bound (already enforced by minLength/maxLength) and alludes to pagination, but never explains limit or offset, and its category guidance is unintelligible, leaving half the parameters effectively undocumented.

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 (Search) and resource (live KeepBal tools and models), which is a clear operation an agent can identify. It is implicitly distinct from siblings like run_tool or inspect_tool, which act on a single known item, though the description never names those siblings to sharpen the boundary.

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/when-not guidance relative to inspect_tool or run_tool. The line 'use category models for models' is the only routing hint and it is cryptic — it never states the parameter name or an exact value, so an agent must guess at intent.

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