Skip to main content
Glama

Server Details

Finds the simplest equation consistent with your data. SINDy and PySR symbolic regression via MCP.

Status
Healthy
Last Tested
Transport
Streamable HTTP
URL

Glama MCP Gateway

Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.

MCP client
Glama
MCP server

Full call logging

Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.

Tool access control

Enable or disable individual tools per connector, so you decide what your agents can and cannot do.

Managed credentials

Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.

Usage analytics

See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.

100% free. Your data is private.
Tool DescriptionsA

Average 4.8/5 across 4 of 4 tools scored.

Server CoherenceA
Disambiguation5/5

Each tool has a clear, non-overlapping purpose: feature_request handles feature requests, pysr_run performs symbolic regression for algebraic equations, pysr_uncertainty provides bootstrap confidence intervals for pysr_run results, and sindy_run identifies differential equations from time series. No ambiguity exists.

Naming Consistency4/5

Tool names are predominantly in snake_case with a pattern of domain prefix plus action (pysr_run, pysr_uncertainty, sindy_run). feature_request deviates from the prefix pattern but still follows verb_noun and is clear. Overall, naming is consistent and predictable.

Tool Count5/5

With 4 tools, the server is well-scoped for its purpose of symbolic regression analysis and feature requests. Each tool serves a distinct and necessary function without redundancy or unnecessary complexity.

Completeness5/5

The tool surface covers the full workflow: algebraic symbolic regression (pysr_run), uncertainty quantification (pysr_uncertainty), and differential equation discovery (sindy_run), plus a mechanism for requesting new features. No obvious gaps in the core capabilities.

Available Tools

4 tools
feature_requestAInspect

Request a feature that Occam doesn't support yet.

Use this when you need a capability that Occam doesn't currently
offer. Requests are logged and used to prioritize development.

Rate limit: 5 requests/hour per IP, 50/hour global — stricter than
the compute tools' 10/hour to prevent log flooding. Descriptions
longer than 500 characters are truncated.
ParametersJSON Schema
NameRequiredDescriptionDefault
descriptionYesA short description of the feature you need. Examples: 'LaTeX output for equations', 'support for ODE constraints', 'GPU-accelerated search', 'larger dataset limits'. Helps prioritize development.

Output Schema

ParametersJSON Schema
NameRequiredDescription
okYes
messageYes
descriptionYes
Behavior5/5

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

Beyond annotations (which don't indicate destructive or read-only behavior), the description adds critical behavioral context: rate limits (5/hour per IP, 50/hour global) and description truncation at 500 characters. This helps the agent understand operational constraints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise (3-4 lines), front-loaded with the core purpose, and every sentence provides unique information (usage, rate limits, truncation). No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple one-parameter tool with an output schema (present but not shown), the description covers: purpose, usage context, behavioral constraints, and parameter guidance. It is fully adequate for correct agent invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%. The description adds value by including concrete examples for the 'description' parameter ('LaTeX output for equations', etc.) and explaining how the input helps prioritize development, going beyond the schema's basic description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Request' and the resource 'a feature that Occam doesn't support yet'. It effectively distinguishes from sibling compute tools (pysr_run, etc.) by indicating a different domain (feature requests vs. scientific computing).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear guidance: 'Use this when you need a capability that Occam doesn't currently offer.' It also includes rate limit and truncation details, though no explicit when-not or alternatives are needed given sibling distinctions.

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

pysr_runA
Read-only
Inspect

Evolutionary Symbolic Regression (PySR).

Discovers algebraic equations y = f(x1, x2, ...) from feature/target
data. Returns a Pareto front ranked by the complexity/accuracy
tradeoff. Slower than SINDy (10-60s); searches often terminate early
on convergence. For differential equations from time series, use
sindy_run instead.

Pricing: free tier up to 100 rows × 8 features, 60s timeout. Beyond
that, $0.25 + $0.03 per 100 extra rows + $0.01 per extra feature
squared, timeout up to 300s (5 min), via x402 (USDC on Base) or
MPP/Stripe. MPP/Stripe adds a flat $0.35 per-transaction fee (Stripe
processing), so the MPP challenge amount in a `payment_required`
response is $0.35 higher than the x402 amount for the same base
price; x402 gets the lower rate. Omit `payment` for free-tier
requests; paid requests without a valid credential receive a
`payment_required` result with pricing and accepted schemes. Full
pricing: occam://pricing

Advisory limits: jobs over 50,000 rows or 20 features are accepted
but may not converge; response carries a top-level `warning`.

Operators: fixed supported set only — custom operators (e.g.
'inv(x) = 1/x') are rejected. Unary: sin, cos, tan, exp, log, log2,
log10, sqrt, abs, sinh, cosh, tanh. Binary: +, -, *, /, ^.
See also prompt `supported_operators`.

Loss metric: `loss` (in `pareto_front[].loss` and `best_loss`) is
mean squared error between model prediction and `y` on the full
training set — not RMSE, and not normalized by Var(y). A threshold
appropriate for one dataset scales with y's magnitude, so set
`loss_threshold` with that in mind (e.g. for y values near 1.0,
1e-6 is a tight fit; for y near 1000, the equivalent is 1.0).

Early termination: set `loss_threshold` to stop at your noise floor.
The server also stops when the search stalls (<1% improvement in the
last third of the budget); disable with `stall_detection=false`.
Response `stop_reason` is one of: loss_threshold, stall, timeout,
natural.

If `feature_names` is supplied, its length must equal the number of
columns in `X`; a mismatch is rejected with a validation error.

Follow-up: call `pysr_uncertainty` with a chosen expression and the
same dataset for bootstrap confidence intervals on its fit constants
and optional prediction bands.

Rate limit: 10 requests/hour per IP, 200/hour global, max queue
depth 20 (shared with sindy_run and pysr_uncertainty).

Response (success) includes `pareto_front[]` (each with `complexity`,
`loss`, `expression`, `expression_latex`), `best_expression`,
`best_expression_latex`, `best_loss`, `best_complexity`, `stop_reason`,
`elapsed_seconds`, `queue_seconds` (>0 = server saturated; use as
backoff signal), optional `warning`, optional `_meta` (MPP receipt).
Full response and payment-required schemas: occam://tool-schemas

Example request:
  X=[[0.0], [1.0], [2.0], [3.0]], y=[1.0, 3.0, 5.0, 7.0],
  feature_names=["x"], max_complexity=10, timeout_seconds=15

Policy: occam://privacy-policy — Citation: occam://citation-info
ParametersJSON Schema
NameRequiredDescriptionDefault
XYes2D array of input features. Each row is an observation, each column is a feature. Free tier: 100 rows, 8 features. Paid tier: up to 50,000 rows, 20 features.
yYesTarget values, one per row of X.
paymentNoPayment credential. Accepts either a JSON object or a JSON-encoded string (FastMCP's transport pre-parses strings whose field annotation is non-bare-`str` into objects, so the object form is canonical; the string form is accepted for legacy callers). Required when the dataset exceeds the free tier (100 rows, 8 variables). Omit for free-tier requests. For x402: {"transaction":"0x...","network":"...","priceToken":"..."}. For MPP/Stripe: {"challenge":{...},"payload":"..."}. For prepaid API key: {"scheme":"prepaid","api_key":"occ_live_...","request_id":"<optional uuid>"}.
populationsNoNumber of evolutionary populations for the search. Default 15, max 20.
feature_namesNoNames for each variable/feature column. Defaults to x0, x1, ...
loss_thresholdNoOptional early-stop threshold on the best loss found. If set, the search terminates as soon as any Pareto-front member reaches a loss at or below this value, even if the timeout has not been reached. Useful when you know your noise floor. Default: None (no user threshold; the search runs until the stall detector or timeout).
max_complexityNoMaximum expression tree size. Higher allows more complex expressions. Default 20, max 25.
stall_detectionNoWhen true (default), the server stops the search early if the best loss has not improved by more than 1% during the last third of the time budget. This reclaims compute once the search has converged. Set to false only if you want the search to run for the full timeout regardless of progress.
timeout_secondsNoWall clock time limit in seconds. Free tier: max 60. Paid tier: max 300 (5 minutes). Default 60.
unary_operatorsNoAllowed unary operators, drawn from the fixed supported set: sin, cos, tan, exp, log, log2, log10, sqrt, abs, sinh, cosh, tanh. Custom operators (e.g. 'inv(x) = 1/x') are NOT supported — only the names listed are accepted. Default: sin, cos, exp, log, sqrt. Pass [] for none.
binary_operatorsNoAllowed binary operators, drawn from the fixed supported set: +, -, *, /, ^. Custom operators are NOT supported. Default: +, -, *, /. Pass [] for none.

Output Schema

ParametersJSON Schema
NameRequiredDescription
warningNo
best_lossNo
stop_reasonNo
pareto_frontNo
queue_secondsNo
best_complexityNo
best_expressionNo
elapsed_secondsNo
best_expression_latexNo
Behavior5/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds significant context: slower runtime (10-60s), early termination behavior, stop_reason values, fixed operators, loss metric being MSE not RMSE, response structure, queue_seconds as backoff signal, and pricing model. This far exceeds what annotations provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but well-structured: starts with purpose, then pricing, operators, loss details, early termination, etc. Each paragraph serves a clear purpose. There is minor redundancy with schema (operators listed again), but overall it is efficiently packed with useful information without unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (evolutionary search, 11 parameters, pricing model), the description covers all aspects: purpose, usage, limitations, pricing, response schema, error handling (stop_reason), follow-up tools, rate limits, advisory limits, and an example. The presence of an output schema does not reduce the burden as the description still adds value.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with good parameter descriptions. The description adds valuable extra meaning: clarifies that loss_threshold is for noise floor, explains stall_detection behavior, lists operator defaults and constraints, and details payment credential formats. This exceeds the baseline of 3 by providing significant additional context.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Evolutionary Symbolic Regression (PySR)' and 'Discovers algebraic equations y = f(x1, x2, ...) from feature/target data', specifying the verb (discovers), resource (algebraic equations), and scope (from feature/target data). It differentiates from sibling 'sindy_run' by noting that it is slower and suggesting 'sindy_run' for differential equations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says 'For differential equations from time series, use sindy_run instead.', providing a clear alternative. It also explains when to use paid vs free tier, describes early termination via loss_threshold and stall_detection, and includes rate limits and advisory limits. This gives comprehensive guidance on when and how to use the tool.

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

pysr_uncertaintyA
Read-only
Inspect

Bootstrap confidence intervals for the numeric constants of a frozen expression, plus optional prediction bands on an x-grid.

Typical flow: call pysr_run, pick an expression from the response
(best_expression or a pareto_front entry), pass it back here with
the same dataset to get CIs on its fit constants.

Returns frequentist bootstrap confidence intervals, not Bayesian
credible intervals — posterior inference over expression structures
is an open research problem. This tool freezes the expression
chosen by the caller and bootstraps only its numeric constants;
uncertainty about *which* expression is correct is not quantified.

Bootstrap semantics:
  - If y_sigma is supplied, uses parametric bootstrap
    (y_b = y + Normal(0, y_sigma)). CI reflects user-stated
    measurement noise.
  - Otherwise uses residual bootstrap: fit once, resample residuals.
    CI reflects estimated-from-residuals noise.

Only Float constants in the expression become free parameters.
Integers stay structural (the 2 in x**2 is a function-class choice,
not a fit constant). Expressions with no Float constants
(e.g. "x + y") will be rejected with a validation error.

Expression grammar: the `expression` string is parsed by sympy.
Accepted operators are the same set pysr_run emits: unary `sin`,
`cos`, `tan`, `exp`, `log`, `log2`, `log10`, `sqrt`, `abs`, `sinh`,
`cosh`, `tanh`; binary `+`, `-`, `*`, `/`, `^` (or `**`). Whitespace
and parenthesization are free. Every free symbol in the expression
must correspond to an entry in `feature_names` — an unrecognised
symbol is silently treated as a fresh sympy Symbol and the fit will
fail downstream rather than reject early. Parse failures (syntax
errors, malformed operators) surface as tool errors.

If `feature_names` is supplied, its length must equal the number of
columns in `X`; a mismatch is rejected with a validation error.

Pricing: always free, regardless of dataset size. This tool has no
`payment` parameter and is never subject to the x402/Stripe gate.
Large bootstrap jobs still count against the shared rate limit
below, so budget `n_resamples` accordingly.

Rate limit: 10 requests/hour per IP, 200/hour global, max queue
depth 20 (shared with sindy_run and pysr_run).
ParametersJSON Schema
NameRequiredDescriptionDefault
XYes2D array of input features. Each row is an observation, each column is a feature. Free tier: 100 rows, 8 features. Paid tier: up to 50,000 rows, 20 features.
yYesTarget values, one per row of X.
alphaNoSignificance level. 0.05 → 95%% CI. Default 0.05.
x_gridNoOptional 2D grid of feature values at which to report a prediction band. Must have the same number of columns as X. Omit to skip prediction-band computation.
y_sigmaNoOptional per-point measurement standard deviations, or a single scalar applied to all points. When supplied, the helper uses parametric bootstrap (y_b = y + Normal(0, y_sigma)); otherwise it uses residual bootstrap. Supplying y_sigma also improves the initial weighted fit.
expressionYesThe expression to bootstrap, as returned by pysr_run (`best_expression` or a `pareto_front[i].expression`). Only numeric Float constants are treated as free parameters — integers in the expression (e.g. the 2 in x**2) stay structural.
n_resamplesNoNumber of bootstrap resamples. Higher = tighter CIs, more compute. Default 100.
feature_namesNoNames for each variable/feature column. Defaults to x0, x1, ...

Output Schema

ParametersJSON Schema
NameRequiredDescription
noteYes
alphaYes
coefficientsYes
prediction_ciNo
bootstrap_methodYes
n_requested_resamplesYes
n_successful_resamplesYes
Behavior5/5

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

The description provides extensive behavioral details beyond annotations, including bootstrap types (parametric vs residual), expression grammar, validation rules, pricing (always free), rate limits, and limitations. It does not contradict the readOnlyHint annotation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured and front-loaded with the core purpose. It is relatively long but each section earns its place by adding unique information. Slight improvements could trim redundancy, but overall it is effectively concise for the tool's complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 8 parameters, high complexity, and an output schema, the description covers all necessary aspects: typical flow, bootstrap semantics, validation, pricing, rate limits, and parameter interactions. It is fully complete for an agent to correctly invoke the tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and the description adds enriched meaning for parameters such as y_sigma (explains parametric vs residual bootstrap), expression (only Float constants are free), and feature_names (default naming). This adds significant value beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it computes 'Bootstrap confidence intervals for the numeric constants of a frozen expression, plus optional prediction bands on an x-grid.' This uses specific verbs and resources, and distinguishes from siblings like pysr_run (which performs initial symbolic regression).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly describes the typical flow: call pysr_run, pick an expression, then use this tool. However, it does not explicitly state when NOT to use it or name specific alternatives beyond mentioning the workflow. It gives clear context for use but lacks exclusion criteria.

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

sindy_runA
Read-onlyIdempotent
Inspect

Sparse Identification of Nonlinear Dynamics (SINDy).

Recovers governing differential equations (dx/dt = f(x)) from time
series data. Returns human-readable sparse expressions. Fast (seconds).
For algebraic y = f(x) relationships without time structure, use
pysr_run instead.

Pricing: free tier up to 100 rows and 8 variables. Beyond that,
$0.05 + $0.01 per 100 extra rows + $0.01 per extra variable squared,
via x402 (USDC on Base) or MPP/Stripe. MPP/Stripe adds a flat $0.35
per-transaction fee (Stripe processing), so the MPP challenge amount
in a `payment_required` response is $0.35 higher than the x402 amount
for the same base price; x402 gets the lower rate. Omit `payment`
for free-tier requests; paid requests without a valid credential
receive a `payment_required` result with pricing and accepted schemes.
Full pricing table as structured JSON: occam://pricing

Advisory limits: jobs over 500,000 rows or 50 variables are accepted
but may not converge within the time budget; the response carries a
top-level `warning` the agent should surface and treat as tentative.

If `feature_names` is supplied, its length must equal the number of
data columns; a mismatch is rejected with a validation error.

Rate limit: 10 requests/hour per IP, 200/hour global, max queue
depth 20 (shared with pysr_run and pysr_uncertainty).

Response (success) includes `equations[]` (each with `variable`,
`equation`, `expression`, `expression_latex`, `r2`), `library_terms`,
`nonzero_terms`, `elapsed_seconds`, `canonical_match` (dict with
`system`, `form`, `variable_map`, `parameter_map`, `confidence` if
the discovered system matches one of Lorenz / Lotka-Volterra /
Van der Pol / Duffing; `null` otherwise), optional `warning`,
optional `_meta` (MPP receipt on paid calls). Full response and
payment-required schemas: occam://tool-schemas

Example request:
  data=[[1.0, 0.0], [0.95, -0.31], [0.81, -0.59]], t=[0.0, 0.1, 0.2],
  feature_names=["x", "y"], poly_degree=2, threshold=0.1

Policy: occam://privacy-policy — Citation: occam://citation-info
ParametersJSON Schema
NameRequiredDescriptionDefault
tYesTimestamps corresponding to each row of data. Length must match row count.
dataYes2D array of time series data. Each row is a timestep, each column is a state variable. Free tier: 100 rows, 8 variables. Paid tier: up to 500,000 rows, 50 variables.
paymentNoPayment credential. Accepts either a JSON object or a JSON-encoded string (FastMCP's transport pre-parses strings whose field annotation is non-bare-`str` into objects, so the object form is canonical; the string form is accepted for legacy callers). Required when the dataset exceeds the free tier (100 rows, 8 variables). Omit for free-tier requests. For x402: {"transaction":"0x...","network":"...","priceToken":"..."}. For MPP/Stripe: {"challenge":{...},"payload":"..."}. For prepaid API key: {"scheme":"prepaid","api_key":"occ_live_...","request_id":"<optional uuid>"}.
max_iterNoMaximum STLSQ optimizer iterations. Default 20.
thresholdNoSTLSQ sparsity threshold. Higher values produce sparser equations. Default 0.1.
poly_degreeNoPolynomial library degree for SINDy candidate functions. Default 2.
feature_namesNoNames for each variable/feature column. Defaults to x0, x1, ...

Output Schema

ParametersJSON Schema
NameRequiredDescription
warningNo
equationsNo
library_termsNo
nonzero_termsNo
canonical_matchNo
elapsed_secondsNo
Behavior5/5

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

Annotations declare readOnlyHint=true and idempotentHint=true. The description adds extensive behavioral details: pricing mechanisms, advisory convergence warnings, validation errors, rate limits (10/hr IP, 200/hr global), queue depth, and response structure including canonical matches. No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but well-structured with clear sections (purpose, alternatives, pricing, limits, validation, rate limits, response, example). Every sentence adds value, and it is front-loaded with the core purpose. Could be slightly trimmed but overall efficient for the complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (7 params, output schema referenced, annotations present), the description covers purpose, usage, pricing, limits, validation, response structure, and examples. It references external schemas for further detail, making it fully complete for an agent to use correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds value by contextualizing limits (e.g., free tier rows/variables in data), detailing payment param formats, and providing an example request. This extra context pushes the score above baseline, though not the maximum.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Sparse Identification of Nonlinear Dynamics (SINDy). Recovers governing differential equations (dx/dt = f(x)) from time series data.' It also distinguishes from sibling 'pysr_run' by noting the alternative for algebraic relationships.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly tells when to use this tool vs. 'pysr_run' ('For algebraic y = f(x) relationships without time structure, use pysr_run instead'). It provides pricing tiers (free vs. paid), advisory limits, and rate limits, giving clear guidance on when to invoke and how to handle payment.

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

Discussions

No comments yet. Be the first to start the discussion!

Try in Browser

Your Connectors

Sign in to create a connector for this server.

Resources