EvaFarm — GPU render nodes

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), yet the description adds genuinely new behavioral facts: billing is per active minute, rounded up, no minimum, and node preparation is not charged. This billing-model disclosure is exactly the kind of context 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?

Front-loads the billing model, then the input modes, then edge cases. It is dense but each sentence carries information; structure is a single flowing paragraph rather than scannable segments, which slightly hurts readability.

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 carry the return-value burden; it implies a single price or a comparison across all catalog configurations but does not state the result shape explicitly. Inputs, billing rules, and the node/nodes_count behavior are otherwise well covered.

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 baseline is 3, but the description adds cross-parameter meaning the schema does not: node label selects that node's rate vs. pricing every configuration when omitted, and nodes_count > 1 split frames evenly across identical nodes. The input-mode relationship between duration params and render params is also clarified.

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 ('Price a rental') plus the billing lens it uses ('the way EvaFarm bills it'). The sibling tools (get_node, list_nodes, rental_guide, service_status) do node lookup, guidance, or status, so cost estimation is unambiguously distinct.

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 operational context for the two valid input modes (a duration in hours/minutes, or a render via frames × seconds_per_frame) and explains what happens with vs. without a node label. It does not name an alternative tool or state any when-not condition, but no real alternative exists among the siblings.

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 fully covered and the description does not contradict it. The description adds only label-format tolerance, not behavioral traits such as error behavior on an unknown label or what 'full details' includes.

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 zero waste; the core purpose leads and the format normalization is parenthetically appended, which is exactly the right priority order.

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, two-parameter lookup with a fully documented schema and no output schema, the description covers what the agent needs to call it. It could have briefly characterized the returned 'full details', but that is a minor gap.

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 genuinely adds meaning beyond the schema by documenting accepted label variants ('3', 'node 3') that the schema's 'NODE_03' example does not mention. It adds nothing about the currency parameter, which the schema already covers.

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 combination ('Full details of one node') and scopes it to a single lookup by label, which implicitly contrasts with the sibling list_nodes. It does not explicitly name or distinguish itself from alternatives like estimate_cost or rental_guide, so it stops just 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?

Usage is only implied: 'one node by its label' suggests single-item retrieval versus list_nodes for enumeration, but there is no explicit when-to-use, when-not-to-use, or named alternative. Nothing misleading, but the agent must infer the routing decision.

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, so the safety profile is covered. The description adds genuine domain semantics annotations cannot express: the meaning of each status value, including the non-obvious 'ai' state (busy with an AI workload until status_until, not for rent), which prevents mis-selecting an unavailable node.

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 catalog payload and its status vocabulary front-loaded before the filtering hint. Slightly run-on in the status parenthetical, but nothing is wasted.

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?

No output schema exists, so the description must convey the return shape — it does so by naming the per-node fields (status, hardware, price, software, engines). It stops short of describing ordering, pagination or result volume, which a catalog tool could reasonably address.

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% with examples for gpu, engine, software, currency and available_only, so the baseline is 3. The description adds only the general framing that these filters target 'a job', not any per-parameter syntax or interaction detail 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+resource ('The EvaFarm node catalog') and enumerates what the listing carries: live status, hardware, hourly price, software and render engines. It does not explicitly contrast itself with sibling list-adjacent tools like get_node or estimate_cost, so it lands 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?

'Filter to find a machine for a job' implies the browse-and-filter use case, but there is no statement of when to prefer this over get_node (single node) or estimate_cost (pricing a job). Usage is implied rather than directed.

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, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuine value beyond that by disclosing the guide's content scope (billing rules, privacy, connection methods) and that it also surfaces links to the app, site and support — the agent knows what kind of payload comes back in the absence of an output schema.

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 no filler: the core purpose comes first, then the topic list. The list is long but each item maps to a real section of the guide, so it earns its 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?

For a static documentation-retrieval tool with no output schema, the description sufficiently covers scope, content topics and supporting links. The only notable omissions are when-to-use guidance and confirmation of the returned format, which are minor given the tool's simplicity.

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 single `language` parameter has 100% schema description coverage with an explicit enum (en/ru) and a default documented in the schema, so the schema does the heavy lifting. The description never mentions language selection or the default, adding nothing beyond the structured field — 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?

The description names the resource (a renting guide for EvaFarm) and enumerates the exact topics it covers — sign-in, projects and wallets, billing, remote-connection via AnyDesk/RustDesk, teams, privacy. That is enough for an agent to know this returns a documentation payload rather than acting on nodes. It stops short of differentiating from siblings, but those (estimate_cost, get_node, list_nodes, service_status) do not overlap in intent, so the risk of confusion is low.

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 only implied: an agent can infer 'call this when the user needs onboarding/renting documentation', but the description never states when to prefer it or what it does not cover for. No alternatives or exclusions are given, and no prerequisites (e.g. does it need auth?) are mentioned.

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 read-only, idempotent, non-destructive, and closed-world behavior. The description adds temporal scope ('right now') and enumerates the counted states, but does not cover caching, rate limits, or output structure. With annotations carrying the safety profile, this is minimally adequate.

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 zero waste. Every word earns its place, and the most important information (what is counted) comes first.

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?

No output schema exists, but the description communicates the return values (counts per node state) and temporal scope ('right now'). For a simple, parameterless summary tool, nothing essential is missing.

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 per the rules. The description adds no parameter semantics because none exist.

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 metric (counts of nodes by state) and resource (nodes), scoped by 'right now'. It does not explicitly differentiate from siblings like list_nodes, but the aggregate counting purpose 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?

Provides no when-to-use guidance, no alternatives, and no prerequisites. Only 'right now' implies a current snapshot context, leaving the agent to infer usage.

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