SCRIPTMASTERLABS — Calibration Court

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

Annotations only declare readOnlyHint=true, so the description earns credit for adding real context beyond them: it discloses that invocation is paid via x402 with USDC on Base (a precondition the agent must surface to the user) and that the operation is stateless with nothing persisted (a data-handling guarantee). It stops short of describing error modes, minimum sample requirements, or return shape.

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 with no filler, and the cost/payment notice is correctly front-loaded so an agent sees the precondition before anything else. The statelessness note lands at the end where it belongs. Nothing is wasted, though the middle sentence packs two distinct operations (fit and apply) without separating them.

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 should at least imply the return value; 'recalibrate the given probabilities' hints at a same-length array of adjusted probabilities but never confirms it. The most consequential gap for a fitting tool is the absence of any minimum-examples or degenerate-input guidance, which is exactly what causes failed calls. Payment and statelessness are well covered, so it is adequate but not 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 0%, so the description must carry the load. It does explain both parameters semantically — 'examples' as labelled {p,y} outcome pairs and 'probs' as the probabilities to recalibrate — which is more than the bare schema offers. But it omits the practical semantics that matter for isotonic fitting: minimum number of examples, whether probs must lie in [0,1], and whether output order/length matches input.

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: fit isotonic calibration on labelled {p,y} outcomes and recalibrate the supplied probabilities. An agent knows exactly what computation happens. However, it never distinguishes itself from the sibling court_recalibrate, which by name covers very similar ground — the key differentiator (user-supplied labels vs. server-side model) is only implied by 'YOUR labelled outcomes'.

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 rather than stated: 'YOUR labelled outcomes' signals the precondition that the caller must already hold labelled pairs, and 'the given probabilities' implies they are passed in. There is no explicit when-to-use/when-not, and the near-identical sibling court_recalibrate is never mentioned as the alternative for callers who lack labels.

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, so safety is covered; the description still adds two things annotations cannot: the call costs nothing and it returns empty lists when nothing has resolved, sparing the agent from treating an empty result as an error. It leaves out ranking direction (whether lower Brier ranks higher) and result-size limits.

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, front-loaded with the resource and metric, with the cost and empty-result caveats following. Nothing is padded or repeated.

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 read-only list tool with no output schema, it covers what the ranking is and the degenerate empty case, but it omits the meaning of the only parameter and the ordering/return shape, leaving gaps an agent must guess at.

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% and the single parameter task_type is never mentioned, so an agent cannot tell whether it filters the leaderboard by task category or is ignored. With low coverage the description should compensate, and it does not.

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 resource (ranking of decision models) plus the ranking metric (Brier score) and population (resolved real-world questions), so an agent can distinguish it from court_model_report, which profiles one model rather than ranking all of them. It stops short of naming those siblings 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?

There is no guidance on when to call this versus court_model_report or court_calibrate_labels, and no mention of prerequisites. 'Free' and the empty-list note describe cost and output behavior, not when-to-use conditions.

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?

readOnlyHint=true already covers the safety profile, so the description's contribution is naming the computed statistics and noting the call is free. It says nothing about authorization needs, rate limits, or whether an unknown model produces an error versus an empty report.

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 front-loaded sentence with no filler; the metric list is dense but each term earns its place. The trailing 'Free.' is a fragment but conveys a real cost signal.

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, no annotation detail, and 0% schema coverage, the description should explain what the report looks like (units, thresholds, drift definition) and what task_type does. Neither is addressed, which is a meaningful gap for a two-parameter analytical tool.

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 carry both parameters. 'For one model' hints at the required `model` argument, but `task_type` is never mentioned anywhere, leaving half the parameters 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 resource (calibration report for one model) and enumerates the concrete metrics returned (Brier, ECE, reliability bins with Wilson intervals, overconfidence, drift). It doesn't name a sibling, but 'for one model' implicitly contrasts with court_leaderboard's multi-model view.

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 statement of when to use this versus court_leaderboard, court_recalibrate, or court_calibrate_labels. The only usage-adjacent signal is 'Free', which speaks to cost, not to when the tool applies.

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 declare readOnlyHint=true; the description adds substantial context on top: this is a paid call settled in USDC on Base, and it will refuse with a named error code when the ledger has fewer than 30 samples. That is real behavioral disclosure an agent needs before calling. It does not clarify whether payment is still charged on refusal, which keeps it from a 5.

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, zero filler, and the cost/failure constraints are front-loaded where an agent will see them before committing. Every clause carries information the schema does not.

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?

There is no output schema, so the description should say what comes back — a calibrated probability value, presumably with sample count or confidence — and it does not. Combined with the unexplained task_type parameter, the definition is workable but leaves gaps an agent would have to discover by calling.

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 3 parameters, so the description must carry the load. It only implicitly conveys 'model' and 'prob' via 'a model's raw probability'; the optional task_type parameter is never mentioned, nor is the expected format of 'model' (name, version, provider) or how prob is interpreted.

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 precise verb and transformation: 'Map a model's raw probability to an empirically calibrated one using resolved outcomes on the ledger.' An agent immediately knows the operation is a probability recalibration, not a report or label fetch. It stops short of naming how it differs from siblings like court_calibrate_labels, so it sits at 4 rather than 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?

The description gives a clear precondition ('refuses with insufficient_data below 30 samples') and a cost signal (paid via x402/USDC), so the agent knows the failure mode. However, it never says when to pick this over court_calibrate_labels or court_model_report, leaving sibling selection 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?

readOnlyHint=true is already declared, and the description is consistent with a safe verification operation. It adds the useful detail of what is actually done (hashing and table cross-checks) and that the call is free, but it omits what happens on a mismatch, whether the scan is expensive, and how results are surfaced.

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 operation front-loaded and the cost hint trailing. Nothing is wasted, though 'Free.' reads as an unexplained fragment rather than earned 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?

With no parameters and no output schema, the description carries the burden of explaining the return value — whether the agent gets a pass/fail verdict, a mismatch list, or counts of checked rows. It does not, which leaves a meaningful gap for an integrity-check tool.

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; there is nothing for the description to disambiguate. It correctly implies a whole-ledger scan with no filterable scope.

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 specific verbs (recompute, cross-check) and concrete resources (SHA-256 hash chain, derived tables), so the operation is unmistakable. It does not, however, distinguish itself from the similarly named sibling court_recalibrate, which an agent could easily confuse with a recompute/verification action.

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 on when to run this versus court_recalibrate or the other audit-style siblings, nor any stated prerequisites. The only usage-adjacent information is the word 'Free', which hints at no credit cost but says nothing about invocation conditions.

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