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

With no annotations at all, the description carries the full burden and does meaningful work: it discloses billing behavior (first 30 days charged from account balance), latency (setup takes minutes), the OS restriction, the one-time root password reveal when ssh_keys is omitted, and the required scope servers:create. It does not say whether the order is cancellable/refundable or what the response contains, 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?

Five short sentences, zero filler, with the core action and the server/shared distinction front-loaded before the operational caveats. Every clause (billing, timing, OS, password, scope) supplies 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 9-parameter, no-annotation, no-output-schema mutation tool this is close to sufficient: cost, latency, OS limit, credential behavior and required scope are all covered. The remaining gap is the return value — the description only implies an order is created that get_order can look up, without saying what identifier comes back.

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; the description earns above that by explaining the kind enum in business terms (server = own root server) and by describing the conditional behavior tied to ssh_keys (no keys → one-time root password). The noroot/confirm_no_root coupling is restated from the schema rather than extended, so it is not a full 5.

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?

Opens with a specific verb and resource ("Order a server ... or a shared account") and immediately disambiguates the two modes via the kind enum. It also names the sibling tools (get_order, get_server) used to follow progress, so an agent can place it among the 19 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?

It states the operational context (setup takes a few minutes, watch it with get_order or get_server) and the hard constraint (Ubuntu 24.04 only), which tells the agent when this tool applies and what to do right after calling it. It stops short of explicit prerequisites like "call list_plans first to get plan/region ids" and offers no when-not-to-use exclusion, leaving that to the schema.

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?

With no annotations, the description carries the full behavioral burden. It usefully discloses billing ('first 30 days are charged from the balance'), the required databases:write scope, and the fact that the plan must be a pg plan with optional standby, but it omits provisioning behavior, response shape, and reversibility/cancellation 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?

Three short sentences, front-loaded with the core action. The billing and scope sentences each add practical value without repetition or filler.

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/mutation tool with no annotations and no output schema, the description covers cost and authorization scope but does not describe what is returned or what happens after ordering. Parameter documentation is fully handled by the schema, leaving the description adequate but incomplete for the mutation context.

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 all five parameters are already documented in the input schema. The description adds some context about plan kind pg and single-node versus standby, but does not add meaning beyond the schema for allow, region, version, or name.

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: 'Order a managed PostgreSQL cluster.' It narrows scope to plan kind pg and single-node/standby, and is clearly distinguishable from sibling tools such as databases_list, databases_get, databases_set_allow, and databases_delete.

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 creation context is implied and the description helpfully points to list_plans for the plan id. However, it never explicitly contrasts this with alternatives or states when not to use it, so usage guidance remains inferred rather than explicit.

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 say destructiveHint=true, but the description adds three facts beyond that: deletion is irreversible, it destroys cluster data, and unused prepaid days are refunded to the balance. The scope requirement is also disclosed. This is meaningful behavioral context an agent cannot get from the annotation or 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?

One dense sentence pair with zero filler: action, data loss, refund, irreversibility, then scope. The most consequential warning (irreversibility) is front-loaded before the permissions note.

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 two-parameter destructive tool with no output schema, nothing material is missing: the irreversible effect, billing consequence, and required scope are all stated, and both parameters are defined in the schema. An agent has everything it needs to decide and call correctly.

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%: both id ("pg-<n> from databases_list") and confirm ("the cluster's name, typed to confirm") are fully documented in the schema. The description adds no parameter-level meaning beyond that, 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: "Delete a managed PostgreSQL cluster and its data," which cleanly separates it from siblings databases_create, databases_get, and databases_list. The named resource plus the destructive scope leaves no ambiguity about what is being acted on.

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?

It signals the critical precondition (requires databases:write scope) and the irreversibility ("Cannot be undone"), which is exactly what an agent needs before committing to a destructive call. It stops short of naming non-destructive alternatives or distinguishing cases where databases_set_allow might be preferred, so it is clear context without explicit 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?

The readOnlyHint=true annotation already establishes the safety profile, and the description adds context the annotations do not: the required auth scope 'databases:read' and an inventory of the returned facets (pooler, standby, allow list). It does not cover error behavior for a missing id, but for a read tool with annotation coverage this is solid added value.

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 telegraphic fragment with zero filler, front-loading the returned content and ending with the scope requirement. The clipped style costs a little readability but wastes no words.

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 one required parameter, no output schema, and a read-only annotation, the description does enough: it says what entity is fetched, what is included in the response, and what scope is needed. Only not-found behavior is left unaddressed.

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 the single parameter is well documented ('Database id from databases_list: pg-<n>'). The description adds nothing about the id argument, 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?

The description names the resource precisely (a single managed PostgreSQL cluster) and enumerates what is returned: status, connection details, pooler, standby, allow list. That clearly separates it from the list/delete/allow-list siblings, though the retrieval verb itself is only implied by the noun phrase.

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: it is a singular-fetch tool, and the schema note 'Database id from databases_list' hints at the list-then-get flow. There is no explicit when-to-use, no exclusion of alternatives such as databases_list, and no mention of what happens for an unknown id.

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 the safety profile is covered; the description adds genuinely new behavioral context by naming the required OAuth scope 'databases:read' and by previewing the fields returned per cluster. It omits pagination or result-limit behavior, which keeps it below 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 short fragments, front-loaded with the resource and its returned attributes, with zero filler. The clipped phrasing ('with status, plan and region. Scope databases:read.') reads as telegraphic notes rather than complete sentences, which slightly hurts readability but not efficiency.

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 parameterless read-only list with no output schema, the description supplies the two things an agent actually needs: what comes back and what scope is required. Only the absence of any result-size or pagination expectation keeps it from being fully 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate and the baseline of 4 applies. The description does not need to compensate for any schema gap here.

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?

Names a specific resource ('Your managed PostgreSQL clusters') and enumerates what each entry carries (status, plan, region), which is more than the title alone provides. It never states the verb explicitly — 'list' must be inferred from the tool name — and it does not distinguish itself from the sibling databases_get, so it stops 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?

There is no statement of when to use this versus databases_get or the other list_* siblings, and no exclusions. The only contextual cue is the required scope, which functions as an auth prerequisite rather than usage 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?

No annotations exist, so the description carries the burden and does disclose the key traits: this is a full replacement (not a merge) of the existing list, an empty list revokes all access, and it requires the databases:write scope. Missing only propagation timing and confirmation of what is returned.

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 verb and resource, then the edge case, then the auth scope. Every clause earns its place and nothing is padded.

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 two-param mutation with a fully documented schema and no output schema, the description covers the essential facts an agent needs: replacement semantics, the empty-list behavior, and the required scope. It stops short of describing the destroy/overwrite risk explicitly or the response shape.

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%, with both params documented ('pg-<n>' id source and 'IP addresses or CIDRs'), so the baseline is 3. The description's 'who may connect' adds a small amount of meaning to `allow` but nothing beyond the schema on `id` or value formatting.

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?

A specific verb ('Replace') plus resource ('a cluster's allow list') with a parenthetical clarifying the semantics ('who may connect'). This is clearly distinct from the other databases_* siblings (list/get/create/delete), which do not touch the allow list at all.

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 purpose implies when to call it, and 'An empty list closes it' gives a concrete usage edge case. However, there is no explicit routing guidance — nothing says to call databases_get first to inspect the current list, or what to do instead when modifying individual entries.

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?

Goes well beyond the destructiveHint=true annotation: it discloses that all data on the server is destroyed, that the action is irreversible, that unused days are credited back to the balance, and which OAuth scope is required. These are exactly the consequences an agent needs before committing to an unrecoverable call.

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 compact sentence packs the effect, the destructiveness, the reversibility, and the scope; the irreversible warning lands early. Zero filler.

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 two-parameter destructive tool with no output schema and fully documented parameters, the description covers the effect, the safety consequence, the billing side effect, and the authorization requirement. An agent has everything needed to call it correctly and cautiously.

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?

Both parameters already carry full schema descriptions, including the srv-<n>/sh-<n> id forms and the typed-name confirmation, so the baseline is 3. The description adds nothing further about the parameters — notably it never mentions the typed-name safety gate itself.

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?

Names a specific verb (delete) and resource (server or shared account) and states the blast radius ('everything on it'), so it is unmistakable against siblings like get_server, power, or resize_server. No other sibling promises deletion, so no disambiguation is needed.

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 the required permission scope ('servers:delete') and warns it cannot be undone, which implies a high-stakes, last-resort operation, but it never says when to prefer it over stop/power-off or how to confirm the target first. Usage is implied 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?

With no annotations, the description carries the full burden; it does disclose the required OAuth scope (dns:write) and that replacement is triggered by supplying the old value, implying a destructive overwrite path. It says nothing about duplicate-record handling, idempotency, or what happens if the zone does not exist.

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 the primary action first, the type list second, the edit path third, and the auth scope last. It is tightly written, though the long parenthetical type list is somewhat expendable.

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 an 11-parameter mutation tool with no annotations and no output schema, the description covers the action, the edit mechanism and auth, which is the minimum viable set. It omits return/response behavior and conflict semantics an agent would want before writing DNS records.

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 every parameter including replace, tag, priority, weight and port is already documented in the schema. The description only re-states the replace semantics and the record-type enumeration, adding no format or interaction details 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 ('Add a record') and enumerates the supported record types, so an agent knows exactly what operation this performs. It does not name or contrast with siblings like dns_delete_record, so it stops short of full differentiation.

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 'or edit one by passing the old value in replace' signals that this same tool handles edits rather than a separate update tool, which is useful. However, there is no guidance on when to prefer this over dns_get_zone/other siblings, no prerequisites beyond the scope string, and no when-not-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?

No annotations are provided, so the description carries the burden. It discloses the required scope ('dns:write') and the optional apex record behavior, but omits side effects, idempotency, error conditions, and what happens if the zone already exists.

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 short sentences with zero waste; the core action is front-loaded and the scope is appended efficiently.

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 two-parameter tool with full schema coverage, the description covers the essential purpose and optional record behavior. However, with no annotations or output schema, it lacks details about the result, activation status, and error scenarios that would make it fully 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%, so the baseline is 3. The description adds minor context by clarifying that the IP parameter corresponds to an apex A/AAAA record, aligning with the schema's description.

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 action ('Host a domain') and resource (DNS zone) with the free tport.cloud nameservers, and mentions the optional apex record. It does not explicitly differentiate from sibling tools like dns_add_record, but the purpose is clear enough for an 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?

Provides no guidance on when to use this tool versus alternatives such as dns_add_record or dns_delete_zone. The scope 'dns:write' hints at permissions but not usage context.

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 flag destructiveHint=true, and the description adds the crucial branch that omitting content deletes EVERY record of that name and type — a high-impact behavior not derivable from annotations. It also discloses the required auth scope (dns:write), which is genuine added context. It stops short of stating irreversibility or no-match behavior.

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 short sentences, front-loaded with the operation and its scope branch, with the auth scope appended. No filler and nothing redundant.

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 four-parameter destructive tool with full schema coverage and no output schema, the definition covers the operation, the bulk-vs-single branch, and the required scope. Missing only edge-case behavior such as no-match results or error shape.

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 would be 3, but the description goes further by explaining the interaction between name/type and content — content narrows the operation to a single matching record. That conditional semantic is the key thing an agent needs and is not spelled out in the schema alone.

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 (delete) and resource (DNS records) with an explicit conditional: all records of a name/type, or the single record matching a value. It does not name the sibling dns_delete_zone as the alternative for zone-level deletion, so the differentiation from siblings is implicit rather than stated.

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 conditional 'or just the one with this value' implies when to supply content versus omit it, which is useful guidance. However, there is no explicit statement of when to choose dns_delete_zone over this tool, and no note on what happens when no records match.

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 destructiveHint=true, but the description adds real value beyond that by disclosing blast radius — deleting the zone also destroys all its records — and the required OAuth scope. It stops short of stating irreversibility/no-undo or that the confirm parameter is a safety gate, which would complete the picture for a destructive operation.

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 short sentences, zero filler, with the action and its consequence front-loaded and the auth constraint trailing. Nothing could be removed without losing 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?

For a 2-parameter destructive tool with no output schema, the description covers what is deleted, the blast radius, and the required scope, while the schema handles the confirm mechanics. It is only slightly short of complete in not flagging that the deletion is irreversible.

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% and both parameters are documented, including that confirm is a typed repeat of the domain, so the baseline is 3. The description adds nothing about either parameter — notably it never mentions that a confirmation string is required, which is the tool's key safety mechanism.

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 ("Delete a zone") with its scope ("and all its records"), which implicitly separates it from dns_delete_record in the sibling list. It does not explicitly name that sibling or dns_get_zone as the read counterpart, so differentiation is inferable rather than stated.

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 versus alternatives, no note that the zone must be empty-checked or that records are deleted implicitly rather than via dns_delete_record. "Scope dns:write" signals an auth prerequisite but is not usage 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=true, so safety is covered. The description adds one useful piece of context — the required dns:read scope, which tells the agent about authorization needs — but says nothing about the shape of the response or whether it is paginated or incomplete for large zones.

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 terse fragments with no filler, and the scope is front-loaded. But the brevity crosses into under-specification: the first sentence omits what the tool actually returns, so conciseness is bought at the cost of clarity.

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 a name/description mismatch, the description leaves the core question unanswered: does it return the zone object or all of its DNS records? For a read tool with no other structured documentation of return values, this gap matters.

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% and the zone parameter is documented with an example ('example.com'), so the description correctly does not repeat it. No additional semantics such as zone-id vs domain-name handling are provided, which is consistent with the baseline for fully documented schemas.

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 phrase 'All records of one zone' indicates the resource and its scope (single zone), which does distinguish it from dns_list_zones. However, it is a noun fragment rather than a verb+resource statement, and it conflicts with the tool name dns_get_zone — an agent cannot tell whether it returns zone metadata or the record set of that zone.

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 guidance on when to use this versus dns_list_zones, get_server, or dns_add_record. The single-zone scope only implies when it is appropriate, leaving the agent to infer the selection criteria.

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 signals a safe read, so the description's added value is the disclosure that results include registrar nameserver settings and available record types, plus the required scope 'dns:read'. It says nothing about result size, pagination, or behavior for accounts with no zones.

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 sentence with no filler; the resource and the payload contents are front-loaded, and the scope is appended last where it belongs. Nothing is repeated or 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?

With no input parameters, no output schema, and annotations covering the safety profile, the description supplies the main missing piece: what the response conceptually contains. Only minor operational details (pagination, empty-state behavior) are absent, which is acceptable at this complexity.

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 schema carries no semantic load and the baseline is a 4. The description correctly implies no filtering inputs are needed.

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?

Names the resource (DNS zones on the free tport.cloud nameservers) and the associated data returned (nameservers to set at the registrar, offered record types), which is enough to distinguish it from the record-level siblings dns_add_record/dns_delete_record. The verb is implicit rather than stated, so it falls short of the verb+resource precision a 5 requires.

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 statement and no reference to alternatives such as dns_get_zone for a single zone or dns_add_zone. For a zero-parameter listing tool the intent is inferable, but the description does not route the agent among 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=true, so the safety profile is covered. The description adds genuinely useful context by disclosing the required auth scope (billing:read), but says nothing about the size or window of "recent ledger lines", whether results are paginated, or the response 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?

Two compact clauses, with the returned data front-loaded and the auth scope trailing. The fragmentary "Scope billing:read." is telegraphic but not wasteful.

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 is the only source of truth about what comes back, and it lists the three result categories. However, it omits how far back "recent" extends and whether there are limits on ledger lines, which an agent needs to interpret 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?

The tool takes zero parameters, so there are no parameter semantics to explain; the baseline of 4 applies. The description correctly implies no inputs are needed to scope the query.

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 concrete resources returned: account balance, monthly spend, and recent ledger lines, which lets an agent distinguish this from the server/DNS/database siblings. It lacks an explicit verb phrase like "Retrieve" but the resource set is unambiguous.

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 needing billing data would select this, but nothing states when to prefer it, when not to use it, or whether it overlaps with get_order. No alternatives are named or ruled out.

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 already declares this is a safe read operation. The description adds the required 'servers:read' scope and enumerates possible progress states, which is useful context, but it does not cover polling behavior or the full 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?

It is very short and front-loaded, with no wasted words. The sentence-fragment style is slightly loose, but the brevity suits a simple getter.

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 getter with no output schema, the description supplies the key return values (progress states and item id) and auth scope. It could mention other order fields, but it is adequate for this 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 coverage is 100%, and the single order_id parameter is documented as returned by create_server or databases_create. The description adds no parameter details beyond what the schema already provides, 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?

The description names the resource (an order) and its progress states, but uses a noun-phrase fragment with no explicit verb such as 'retrieve'. An agent can infer it fetches order status, yet the intended action is implicit rather than stated.

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 use this versus list_servers, get_server, or the create tools that produce order ids. The schema mentions create_server and databases_create, but the description itself gives no usage 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 already declare readOnlyHint=true, but the description adds meaningful context beyond them: the required 'servers:read' scope (an auth prerequisite) and an inventory of what is returned, including recent events. It doesn't cover behavior for an unknown or unauthorized id, which keeps it short of 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?

The field inventory is front-loaded and the scope note trails as a compact qualifier; there is no filler. The telegraphic fragment style is dense but slightly less scannable than a full sentence.

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-record read tool with a fully documented one-parameter schema and read-only annotations, the description covers the resource, the return content, and the auth scope. Only error/not-found behavior is left unstated, a minor gap at this complexity level.

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 the id field already documents the srv-<n> / sh-<n> format and its origin in list_servers. The description adds nothing about the parameter, 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?

The description names the specific resource (one server or shared account) and enumerates the detail fields returned (status, IP, plan, price, paid until, recent events), which clearly separates it from the list_servers sibling. The verb is implied by 'in detail' rather than stated, but the intent is unambiguous.

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 single-server scope implies it is the follow-up to list_servers, and the schema's id description reinforces that by naming list_servers as the source. However, there is no explicit when-to-use or when-not guidance and no named alternative for bulk or filtered retrieval.

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 establishes the safety profile, and 'No key needed' adds genuinely useful auth context not present in annotations. However, nothing is said about whether this returns the full catalog at once, whether results are filtered by the single parameter, or anything about the shape of the response.

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?

It is compact, but the semicolon-delimited content inventory is hard to parse and is not front-loaded with a clear statement of what the tool does. The 'No key needed' note is buried at the end rather than leading with purpose.

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 one optional parameter, the description should at minimum explain what is returned and how 'kind' narrows results. It conveys the catalog's breadth but leaves the caller guessing about return structure and filtering behavior.

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 'kind' parameter (shared, root, pg) is already documented in the schema. The description never mentions the filter at all, so it adds no meaning beyond the schema—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 frames the tool as a catalog lookup ('What can be ordered') and enumerates the resources it exposes—plans with price/vCPU/RAM/disk, regions, images, installs, and plan-region availability. This usefully expands on the name 'list_plans', which alone would suggest plans only, but it never states the action as a clear verb and reads as a content inventory rather than a definition.

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 siblings such as get_billing, create_server, or get_order, nor any prerequisite or exclusion. The only usage-adjacent cue is 'No key needed', which addresses authentication, not selection between tools.

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 the safety profile is covered; the description adds value by disclosing the required OAuth-style scope 'servers:read' and specifying which fields come back. It does not mention pagination or result limits, which would have completed the 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?

Two short fragments with zero padding, and the resource identification is front-loaded ahead of the scope note. The telegraphic style is efficient though slightly clipped rather than fully sentence-structured.

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 tool with no output schema, the description supplies the two things an agent actually needs: what is returned and what scope is required. Only pagination/volume expectations are 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; there is nothing for the description to disambiguate. The field list ('status, plan, region and IP') is arguably more about output than input, but it does not confuse parameter 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?

The description names a specific resource (servers and shared accounts) and enumerates the fields returned (status, plan, region, IP), which distinguishes it from get_server (single server) and create_server. It lacks an explicit verb but the plural resource plus field list makes the list operation unambiguous.

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?

Listing 'your servers' implies the no-argument, list-everything use case, but there is no explicit guidance on when to use this versus get_server for a single server, nor any stated exclusions or prerequisites beyond the scope requirement.

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?

With no annotations, the description carries the full behavioral burden, yet it only implies mutation via the verbs. It does not disclose whether restart causes downtime, whether the operation is asynchronous, how failures are surfaced, or that only certain server states permit each action.

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 tight sentence with the core action front-loaded and no filler. It is efficient, though its terseness borders on under-specification rather than optimal conciseness.

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 mutation tool with no annotations and no output schema, the description leaves too much unsaid: no return value, no async/downtime behavior, no precondition on server state. The permission scope is the only supplementary detail provided.

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 only 50%: id has a documentation string, while action is a bare enum with no description. The description adds nothing about either parameter (e.g., what srv- vs sh- ids mean beyond the schema, or restart semantics), so it fails to compensate for the coverage gap.

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 set (start/stop/restart) and an explicit resource (a server), so the action is unambiguous. It does not name or contrast with siblings such as create_server, delete_server, or resize_server, so it stops short of full differentiation.

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?

"Scope servers:power" states the required permission scope, not when to choose this tool over alternatives. There is no guidance on when to use power vs. delete_server/create_server, nor any prerequisite or state conditions (e.g., server must be stopped before delete).

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?

With no annotations, the description carries the full load and does well: it discloses immediate prorated charging from balance, that the new price takes effect afterwards, and that downgrades are rejected. It omits whether the server is rebooted or taken offline during the resize, and whether an order record is produced (get_order exists), which are the remaining behavioral unknowns.

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?

Four short sentences, front-loaded with the action, then billing consequence, then the failure condition, then the required scope. No filler.

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 two-parameter mutation with no annotations and no output schema, the description covers the action, cost implications, and refusal condition. The main omissions are the operational impact (downtime/reboot) and any indication of what the call returns or whether an order is generated.

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% and both parameters already document their expected formats (srv-<n>/sh-<n> from list_servers, plan id from list_plans). The description adds the constraint that the plan must be larger and of the same kind, but adds no syntax or format detail beyond the schema, so 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 precise verb+resource: promote a server or shared account to a larger plan of the same kind. It is immediately distinguishable from create_server, delete_server, and list_plans, and the 'same kind' qualifier rules out cross-type moves.

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?

Explicitly bounds the operation with 'up to a bigger plan' and 'Smaller plans are refused', which tells the agent when the call will fail. It does not name alternatives, but there is no sibling that competes with this action, so the guidance is adequate.

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