Tuatara Decide

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

Annotations already declare this is a non-read-only, non-idempotent, non-destructive creation. The description adds genuinely useful context beyond them: ~1 minute training time, dependence on the account's NEXUS plan, and the Free-plan cap of 1 classifier. It does not explain what happens on plan-limit exhaustion or what the response contains.

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 zero padding. The purpose and constraints lead, followed by cost/latency facts, so the most decision-relevant information is front-loaded.

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 creation tool with no output schema, the description covers constraints, latency, and plan gating. The only notable omission is what the call returns (e.g., a classifier identifier) needed to chain into decide_predict or get_decide_classifier.

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 baseline is 3, but the description adds constraints the schema does not carry: at least 2 examples per label and a maximum of 255 labels. This materially shapes how examples must be composed.

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 concrete verb and resource ('train a text classifier') with scope qualifiers (labelled examples, label limits), so an agent can distinguish it from get_decide_classifier or list_decide_classifiers at a glance. It stops short of explicitly naming the sibling read tools as alternatives.

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 resource name and the example requirements, but there is no explicit when-to-use or when-not-to-use guidance, and no alternative tool (e.g., decide_predict for inference, get_decide_classifier for retrieval) is named. The constraints hint at the context without routing the agent.

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=false, idempotentHint=false, and destructiveHint=false; the description goes further by disclosing the billing model ('each text counts as one decision on the account's plan'), which explains the non-idempotent, costly nature of the call. It also describes the per-result shape (label, confidence, all label probabilities, unsure flag) in the absence of an output schema. Remaining gaps: no error or failure behavior when a classifier is not ready.

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 dense sentences, front-loaded with the verb and scope, then return shape, then cost. No filler or redundancy; every clause carries information an agent needs.

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 batch inference tool with no output schema, the description covers purpose, batch limit, result fields, and cost. It is slightly short on edge behavior such as what happens when both 'text' and 'texts' are supplied or when a classifier is untrained.

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, but the description adds real meaning beyond the schema by imposing the 256-text batch cap, an operational constraint absent from the parameter definitions. It does not, however, clarify the single 'text' versus 'texts' array usage.

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: labeling texts with a ready classifier, with a concrete batch limit of 256. This is clearly distinct from sibling tools like decide_create_classifier or get_decide_classifier, though the description never names them explicitly to route the agent.

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 phrase 'with a ready classifier' implies the prerequisite that a classifier must already exist (created via decide_create_classifier), which is useful context. However there is no explicit when-to-use guidance, and nothing tells the agent how to choose between the 'text' and 'texts' parameters.

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, idempotentHint and non-destructive, so safety is covered. The description adds real behavioral context beyond that: the async lifecycle (queued/training/ready/failed) and the instruction to poll, which tells the agent this is a non-terminal-state resource that may need repeated calls.

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: identity and return contents first, usage instruction second. No filler, no restatement of the title, and the poll instruction is placed where it will be read.

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 what comes back (status, labels, expected accuracy) and explains the polling workflow needed to use it. It could still mention behavior on an unknown or invalid classifier_id, but for a one-param read tool 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 there is a single required parameter, so the schema already carries the semantics. The description says it fetches 'one classifier' but adds no format or ID-convention detail beyond the schema's own 'dc_...' example. 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?

States a specific verb and resource ('Tuatara Decide: one classifier's status') and enumerates the status domain. The word 'one' implicitly separates it from list_decide_classifiers and decide_predict, but it never names those siblings explicitly, so differentiation is by inference rather than by statement.

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?

'Poll this after creating one' gives a clear use condition tied to the create sibling flow. It does not state when not to use it (e.g. use list_decide_classifiers for all classifiers, or decide_predict once status is ready), so it stops short of full routing guidance.

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, idempotentHint, destructiveHint=false, and openWorldHint=false. The description's 'Read-only' is redundant with those, but 'no auth' is genuinely additional operational context. It adds little else (no rate limits, no format), so a 3 is fair.

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 listing the content areas with no filler. It is efficient, though the compressed comma-list style is slightly dense.

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 zero-parameter, read-only info tool with no output schema, the description tells the agent enough: it is static reference content with no auth needed. The only real gap is not saying when to prefer it over the classifier-specific siblings.

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 of 4 applies; there is no parameter semantics to get wrong. The description correctly implies a static, argument-free retrieval.

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 specific resource (Tuatara Decide) and enumerates exactly what it returns: product explanation, NEXUS plan allowances, limits, and benchmark evidence. This clearly distinguishes it from siblings like get_decide_classifier, list_decide_classifiers, and decide_predict, which deal with concrete classifiers/predictions rather than product docs.

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 guidance and no alternatives named. An agent must infer that this is the 'read the docs first' call before using decide_create_classifier or decide_predict; nothing states that, nor any exclusion.

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, idempotentHint, destructiveHint=false, and openWorldHint=false, so the safety profile is clear. The description adds that the tool returns user-specific data ('your classifiers... your plan... weekly decisions'), which is useful scope context beyond annotations. However, it does not disclose authentication requirements, rate limits, or return format details.

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 a single sentence fragment that is not front-loaded with a clear action. While short, it is under-specified and leaves the core purpose ambiguous, rather than being concise and informative.

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 clearly explain what the tool returns. It hints at classifiers, plan, limit, and weekly decisions, but the phrasing is vague and does not provide a usable return-value overview 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?

The tool takes zero parameters, so there is nothing for the description to clarify. Schema description coverage is 100% and no parameters exist, meeting the baseline score of 4.

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 is a fragment that names resources ('your classifiers', 'your plan', 'classifier limit', 'weekly decisions') without a clear verb like 'list' or 'retrieve'. It does not distinguish the tool from siblings such as get_decide_classifier or decide_create_classifier.

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 use this tool versus alternatives is provided. There is no indication of prerequisites, context, or exclusions.

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 cover the safety profile (readOnlyHint=false, idempotentHint=false). The description adds behavior annotations don't carry: the key is 'shown once,' the call needs no existing credentials, and how the returned credential should be supplied on subsequent calls. It does not mention rate limits or failure modes, so a 4 rather than 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?

Front-loads the purpose and the one-time-key caveat before the usage instructions, and the example is concrete rather than filler. The sentence is long and could be split, but every clause carries 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?

Despite having no output schema, the description names the return values (api_key, agent_id) and the one-time display constraint, and explains the bootstrap/authentication flow. An agent has everything needed to call it once and use the result.

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 name, contact_email, intended_use, and via are all already documented at the source. The description adds no semantics for these four inputs (its api_key mention belongs to later tools, not this schema), so the 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?

Specific verb+resource (register the agent, obtain its API key) and explicitly identifies itself as the MCP equivalent of a named REST endpoint. No sibling tool competes for this purpose, so disambiguation is inherent.

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?

States 'no key needed' and gives the full follow-up path: either attach the key as an X-API-Key/Bearer header or pass it as the api_key argument on later calls, with a concrete example (get_deposit_address). There is no 'when not to use' because no alternative registration tool exists, but the post-conditions are unusually clear.

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