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

Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=false and idempotentHint=false, so the agent knows this is a local, non-destructive write. The description adds only that the result is an empty collection; it doesn't say what happens on a name collision, which matters given idempotentHint=false, nor whether the collection is immediately usable by save_request.

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 filler. The operation is named first and the rationale for it follows immediately.

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 three-parameter local write with full schema coverage and no output schema, the description covers the essentials. The remaining minor gap is duplicate-name behavior, which an agent might guess wrong given idempotentHint=false.

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 all three parameters (name, workspace, description) are documented in the schema, so the schema does the heavy lifting. The description adds no semantics beyond that, which is the baseline case for a fully-documented 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 ('Create an empty collection in the workspace') and adds scope ('empty') plus the downstream consumer ('for save_request to put requests in'). That distinguishes it from the read/mutation siblings, though it doesn't explicitly contrast with delete_request or list_requests.

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 'for save_request to put requests in' implies the workflow context: create a container first, then save requests into it. No explicit exclusions or alternatives are named, but among the siblings there is no competing create-container tool, so the context is sufficient.

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, idempotentHint=true, and readOnlyHint=false, so the safety profile is covered; the description adds genuine value beyond that by disclosing that examples are deleted along with the request and that deletion surfaces in the next Git commit and is restorable from history. It stops short of stating permission requirements or what happens outside a Git workspace.

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 sentences, zero waste, with the mutation and its cascade front-loaded before the recovery caveat. 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 one-parameter destructive mutation with full annotation coverage and no output schema, the description covers cascade effects and recoverability, which is most of what an agent needs. It omits permission/prerequisite expectations and the permanence of deletion in non-Git workspaces (only implied).

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 'request' parameter is documented as an id or Collection/Folder/Name path, so the schema carries the load. The description adds nothing about accepted path forms or how an ambiguous name is resolved, so the baseline of 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 (delete) and resource (saved request) plus the cascading scope ('and its examples'), which an agent can immediately separate from save_request, get_request, and list_requests. The Git-workspace clause further scopes what the operation affects.

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?

Deleting a saved request is self-evidently the inverse of save_request, and the Git clause hints at when recovery is possible, but the description never explicitly says when to use this versus alternatives like create_collection or how to handle a request that merely needs editing. 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?

Goes well beyond the readOnlyHint/openWorldHint annotations by enumerating what the result contains (status, error, failed tests, unset variables, diff versus saved example, cause hints) and by disclosing that secrets are masked. For a read-only diagnostic with no output schema, this is the exact behavioral detail an agent needs.

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?

Purpose is front-loaded in the first sentence, followed by default behavior and return contents. The middle sentence is a dense enumeration but every clause carries information; no filler or restated title text.

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 carries the return-value burden and does so thoroughly, including the masking caveat. Both optional parameters have defaults explained, so an agent can call it with zero arguments and predict the output 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 both parameters are already documented. The description adds only one piece of real meaning — that 'failure' spans no-response, 4xx/5xx, or failing tests — which sharpens the default for `entry` but does not explain the `environment` parameter's effect on variable checking.

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: 'Explain why a request sent from the Kurlo app failed.' The diagnostic framing is clearly distinct from data-retrieval siblings like get_history_entry or list_history, though it never names an alternative explicitly.

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

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

Gives clear usage context by defining the default trigger condition — 'the most recent request that got no response, a 4xx or 5xx status, or failing tests' — so an agent knows it can be called with no arguments after a failure. No explicit when-not or named alternative is provided.

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 annotations by disclosing that from:run actually fires the request ('it creates what a POST creates'), which is a real external side effect, and by documenting merge/dedup semantics for existing test scripts. It does not discuss auth requirements, rate limits, or what happens on network failure, so it stops short of full disclosure.

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 core capability is front-loaded and the two-mode branching is stated early, with no filler sentences. It is dense and slightly run-on, and the mock-example behavior is buried mid-sentence rather than given its own clause, but overall it is efficiently packed for a 12-parameter tool.

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?

Given 12 parameters and no output schema, the description does the heavy lifting on the run/example distinction and the side-effect profile, which are the hardest things to infer. It omits any hint of the return value (e.g. the generated test script or example id) and says nothing about the tuning parameters, so it is complete enough to call correctly but not fully self-contained.

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%, but the description still adds genuine meaning: it explains that `schema` overrides one inferred from the response (e.g. derived from a code type), and that duplicate-named tests are not added, which clarifies the `replace` semantics. Some parameters (variables, environment, allowErrorStatus, exampleName) are left entirely to 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 and resource ('Write pm.test assertions into a saved request') and enumerates exactly what gets asserted: status, Content-Type, and a JSON schema of the body. It also carves out its own scope against siblings like send_request and save_example by explaining that it both tests and persists the response as a mock example.

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 branches on the `from` parameter: 'run (default) sends the request' versus 'example ... for an API that is not running anywhere yet,' naming the precondition that selects each mode. It also states the merge rule up front ('Tests the request already has are kept; a test with the same name is not added twice'), leaving nothing for the agent to infer.

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 establish readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuinely non-obvious behavior beyond that: secrets are masked in the returned data, and the default-to-newest behavior when no entry is supplied. Response size limiting is left to the schema rather than elaborated here.

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 tight sentences, each carrying distinct information: what is returned, the no-argument default, and the masking guarantee. Front-loaded with the primary action; 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?

With no output schema, the description compensates well by enumerating the returned fields (status, headers, body, errors, test results, script logs) and flagging secret masking. Combined with the fully documented two-parameter schema and read-only annotations, nothing an agent needs to invoke it correctly 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?

Schema description coverage is 100%, so both parameters are already fully documented, including the "last" sentinel and the byte cap with defaults. The description's restatement that omitting entry returns the newest adds slight reinforcement but no new 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?

States a precise verb and resource ('Show one request the user sent ... and the response they got') and enumerates the payload contents (status, headers, body, errors, test results, script logs). This is clearly distinguishable from list_history (which yields ids) and from send_request-style siblings.

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 an explicit zero-argument usage path ('Without entry it shows the last one sent, so "why did my last request fail?" needs no other input'), which tells the agent exactly when no parameters are needed. It does not, however, contrast itself with the sibling diagnose_last_failure, which occupies overlapping territory.

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 and openWorldHint=false, so the low bar for safety is covered. The description adds genuinely new behavioral context: that credentials are excluded from the returned definition and that saved example responses are included for comparison, both of which matter for how an agent interprets the output.

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 field enumeration is dense but each item tells the agent what to expect in the response. Slightly long-tailed, but no sentence 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?

There is no output schema, so the description usefully compensates by enumerating the returned contents and the credentials exclusion. What remains unstated is error behavior for an unresolvable id/path/name, which is a minor gap for a single-parameter read 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?

Only one parameter exists and the schema documents it at 100% coverage ('Request id, path (Collection/Folder/Name) or name'). The description adds nothing beyond that about accepted identifier forms, so the baseline of 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 ('Show') and resource ('saved request'), and enumerates the fields returned, so an agent knows this is a definition/metadata read rather than an execution. It does not name the closely competing siblings (send_request, run_request), leaving the read-vs-execute distinction implicit.

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 'saved request ... to compare a live response against', which hints at inspection before or after a send. However, there is no explicit statement of when to prefer this over send_request or run_request, and no stated alternatives 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 and openWorldHint=false, so the safety profile is covered. The description adds real value beyond that with 'Secret values are hidden,' warning the agent that secret variables will be redacted rather than returned — a behavior it could otherwise misinterpret as missing data. It stops short of describing ordering, pagination, or whether inactive environments are included.

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 waste, with the scope stated first and the redaction caveat immediately after. Nothing redundant with the title or annotations.

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-param read-only listing with no output schema, the definition covers the essentials: what is returned and the one surprising behavior (hidden secrets). It could be marginally stronger by noting whether all environments are returned or whether the list is scoped/filtered, but nothing critical to correct invocation 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. There is nothing for the description to disambiguate, and it correctly avoids inventing parameter discussion.

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: 'List the workspace's environments and their variables.' An agent immediately knows the scope (workspace-level) and payload (environments plus their variables). No sibling tool overlaps with environments, so explicit differentiation isn't needed, but there's also no framing of how this relates to the request/collection tools around it.

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 infers it should call this to discover environments before reading or setting variables. There is no explicit statement of when to use this versus alternatives (e.g., set_variable), and no prerequisites or follow-up guidance. Adequate but leaves routing to inference.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety and scope are covered. The description adds useful behavior: results are newest first, scoped to this machine, and include status, timing, and originating saved request. It does not explain pagination or return shape beyond that, but the schema covers the limit parameter.

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 two sentences and front-loads the core purpose before adding the usage cue and follow-up tool. There is no redundant or filler text.

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 read-only list tool with a fully documented schema and annotations covering safety, the description supplies enough context: recent local scope, ordering, returned fields, and follow-up behavior. The main remaining gap is an explicit differentiation from list_requests.

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 all three parameters are already documented in the schema. The description does not add parameter-specific meaning beyond what the schema provides, which is the expected baseline when schema coverage is high.

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 specific verb and resource: list recent requests sent from Kurlo on this machine, newest first. It clearly indicates the content includes status, timing, and source saved request. It does not explicitly distinguish itself from the sibling list_requests, 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?

It gives a concrete trigger: use when the user refers to something they just sent or saw in Kurlo. It also routes the agent to get_history_entry for reading one entry. It lacks explicit guidance on when to prefer list_requests instead, so a 4 is appropriate.

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 and openWorldHint=false, so safety is covered. The description adds useful context beyond that by naming the fields each entry carries (collection, folder, protocol, method, URL), which is valuable given there is no 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?

Two short sentences, zero waste, with the verb and scope front-loaded ahead of the cross-reference to run_request/get_request.

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 the returned fields, and the annotations cover the safety profile. Pagination/ordering behavior is not mentioned, which is the only notable gap for a listing 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 both parameters (query, collection) are documented there with examples and semantics. The description says nothing about the filters, so it adds no meaning beyond the schema — baseline 3.

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 ('List the saved requests in the workspace') plus the fields returned, and links to the sibling tools that consume the resulting ids. This clearly separates it from list_history and list_environments.

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 second sentence tells the agent why it would call this: to obtain the path/id that run_request and get_request require. It gives clear context but no explicit exclusions (e.g., when to prefer list_history or search-style filtering).

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 and openWorldHint=true, so the description earns its keep by disclosing execution semantics: requests run in order, test scripts execute, realtime requests are skipped, and progress is streamed per request when a progressToken is present. It does not say that the requests themselves may mutate external state, which is the main residual risk for an open-world write-hinted tool.

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 tight sentences, front-loaded with the core action and return shape, then the exclusion and the progress behavior. No sentence is 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?

With no output schema, the description supplies the return shape ('pass/fail summary per request') and the skip rule, which is the essential missing structured data. The remaining gap is that none of the five parameters' effects on side effects (e.g., failFast leaving later requests unrun) are spelled out.

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 goes beyond it by tying the collection/folder pair to the run scope and by explaining the call-level progressToken, which does not appear in the input schema at all. No syntax hints are added for variables or environment, but the schema already covers those.

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 with scope: runs the HTTP and GraphQL requests of a collection or folder, in order, with test scripts, returning per-request pass/fail. The 'collection or folder' scope implicitly separates it from the single-request siblings (run_request, send_request), though it never names them.

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 'Realtime requests are skipped' caveat and the ordering/test-script behavior imply when this tool is appropriate (whole-collection batches rather than a single call), but there is no explicit 'use this instead of run_request/send_request when…' routing. An agent must infer the boundary from the family of sibling names.

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 and openWorldHint=true; the description adds that collection defaults, auth and scripts execute, which tells the agent the call can have real side effects beyond a plain read. It stops short of saying whether runs are recorded in history or how failures surface, but the execution semantics are meaningfully disclosed.

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 covering action, inputs inherited, and returned data, with no filler. Every clause earns its place.

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, and the six parameters are fully documented in the schema. The remaining gap is routing guidance against send_request/run_collection and any note on side effects or history recording.

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%, including detailed notes on browserOrigin and browserCredentials, so the schema carries the parameter burden. The description adds no parameter-level detail beyond the general mention of defaults and auth; 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 ('Send one saved HTTP or GraphQL request') and enumerates the return payload (status, headers, body, timings, test results). The word 'one saved' implicitly separates it from run_collection and send_request, but no sibling is named explicitly.

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

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

Usage is only implied through the phrase 'saved request' -- an agent must infer that ad-hoc sends belong to send_request and bulk runs to run_collection. There is no explicit when-to-use, when-not-to-use, or prerequisite statement.

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?

Well beyond the annotations, it discloses that examples are served by the mock server and used as comparison baselines, that the implicit-capture path draws from the last run in the current session, and that secrets and cookies are stripped from the captured response. It leaves open whether saving under an existing name overwrites or duplicates, which matters given idempotentHint=false.

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 sentences, front-loaded with purpose before behavior and mode switching; no filler. The middle sentence is dense, packing mock-server role, comparison use, default capture, and scrubbing into one run-on, 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?

For a non-destructive write tool with full schema coverage and no output schema, the description covers both invocation modes and the notable side effect of secret/cookie removal. Remaining gaps are the response shape and collision/overwrite semantics for the name parameter.

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 real semantics by showing that status and body together constitute an alternate mode rather than independent optional fields. It does not clarify headers/contentType interplay beyond what the schema already says.

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 first sentence states a specific verb and resource: saving an example response on a saved request. The description then distinguishes the tool from nearby siblings like run_request and send_request by explaining that examples are what Kurlo's mock server serves and what live responses are compared against.

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 explicitly splits the two calling modes: omit status/body to capture the last run_request of that request in this session, or supply status and body to record a described response. That is a clear when-to-do-what rule. It does not, however, contrast with save_request or state prerequisites such as whether the request must already be saved.

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?

Beyond the annotations, it discloses the surprising behaviors an agent must know: params/headers/form wholesale replacement, partial-update semantics for everything else, and the hard rule that secrets must be {{variable}} references rather than literals. It also states what testScript/preRequestScript actually are (JavaScript with the pm.* API), which 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-loaded with create-vs-update, then replacement semantics, then constraints and script guidance — a sensible order with little waste. The inline pm.test example is illustrative but runs long for what it conveys.

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 18-parameter mutation with no output schema, the description covers mode selection, replacement behavior, variable/secret conventions, and script semantics. It stops short of saying what is returned (e.g. the saved request's id), which the agent would need to chain into run_request or send_request.

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 94%, so nearly every parameter is already self-documenting, and most description content (list replacement, url required for new requests, default GET) restates the schema. The genuine addition is the cross-cutting {{variables}} and secret-as-variable convention, which is useful but marginal against an already strong 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?

The opening sentence gives a specific verb pair and resource: create or change a saved HTTP/GraphQL request. The word "saved" implicitly separates it from send_request and run_request, but no sibling is named, so the agent must infer the persistence distinction.

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 explicitly resolves the main ambiguity: omit `request` to create, pass an id or path to update, and only passed fields change. What's absent is routing advice against alternatives such as send_request or save_example when the agent is unsure whether to persist at all.

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=false and openWorldHint=true, so the agent knows this can make external, non-read-only calls. The description adds useful context that the request is not persisted and that {{variables}} are resolved from the environment, but it does not discuss side effects, authentication, redirects, or response truncation.

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 tightly written sentences with no filler. The key constraint, that the request is one-off and unsaved, is front-loaded before the variable-resolution 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 9-parameter, open-world HTTP tool with no output schema, the description is adequate but thin. The rich input schema covers parameters well, yet the description does not explain response behavior, error handling, or the safety implications of sending real external requests.

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 schema carries most parameter detail, and the baseline would be 3. The description adds cross-cutting semantic value by explaining that {{variables}} in the URL, headers, and body are resolved from the environment, which the schema only partially states for the url field.

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 gives a specific verb and resource: sending a one-off HTTP request that is not saved in the workspace. This scope distinguishes it from saved-request tools, but it does not explicitly name a sibling such as run_request as the alternative.

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 'one-off HTTP request that is not saved in the workspace' clearly indicates the transient use case. It stops short of explicit when-not guidance or naming alternative tools for saved requests.

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 annotations by disclosing that the value is persisted to the environment's file and shared through Git, and that a missing environment is created as a side effect. It does not say what happens when the key already exists (overwrite vs error), which matters given idempotentHint=false.

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 tight sentences: capability, persistence/Git implication, then the security boundary. Front-loaded with the action and scoping constraint, with 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?

With no output schema and full schema coverage, the description supplies the missing behavioral context: Git persistence, non-secret constraint, and environment auto-creation. Only the overwrite behavior for an existing key is left unexplained.

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 all five parameters are already documented, including the environment default and workspace disambiguation. The description adds no additional parameter meaning, 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?

States a specific verb and resource (set a non-secret variable in an environment) and immediately scopes it away from secrets and protected environments. An agent can distinguish this from list_environments or save_request without reading the 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?

Explicitly names the negative case: 'never use it for a secret' and directs secret/protected changes to Kurlo. It also documents the side effect of creating a missing environment. What's missing is a positive routing rule toward a sibling tool (e.g., when to prefer list_environments first), but the exclusions are strong.

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