knowbase

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

With no annotations provided, the description carries the full behavioral burden, and it does substantial work: it explains what a resolved response includes, warns against claiming success on unresolved outcomes, and discloses that Knowbase validates recipe/statuses but does not inspect the caller's environment or authenticate the lookup id. It does not detail side effects or error responses, but the key trust and boundary information is present.

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 compact and front-loaded, opening with the tool's role in the workflow and then covering action, success criteria, failure handling, and validation boundaries in four efficient sentences. Every sentence contributes distinct information, and there is no filler or redundant schema repetition.

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 the tool's complexity (7 required parameters, no output schema, no annotations), the description provides a solid workflow anchor and explains the high-level output contract (receipt and final report) plus the unresolved/inconclusive behavior. It does not fully specify the response structure beyond that, but the rich parameter schema compensates for most gaps.

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 each parameter already has a clear description, including the important 'returned by diagnosis' relationship and the criterion status enum. The description adds a high-level instruction to submit the ids and observations, but this largely restates what the schema already communicates. The baseline of 3 is appropriate because the schema is doing the heavy lifting.

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 concrete action ('Close the loop after knowbase_diagnose identifies a structured resolution') and specifies what the tool does: apply every listed step, run every verification criterion, and submit ids and observations. This clearly distinguishes it from sibling tools because it is explicitly positioned as the post-diagnosis completion step.

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 clearly states when the tool is appropriate: after knowbase_diagnose has identified a structured resolution. It also provides behavioral guidance for unresolved or verification_inconclusive responses, telling the agent not to claim success, to follow nextAction, and to call the tool again. It does not exhaustively contrast against every sibling, but the sequential relationship to knowbase_diagnose is clear.

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 and does so well: it discloses that the tool rules out causes with reasons, includes fix steps in its answer, and explicitly refuses to guess when observations are insufficient. These are meaningful behavioral expectations beyond the title and 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?

Three sentences with no filler: the first gives the core behavior, the second gives usage timing and output contents, the third gives the honesty fallback. Everything earns its place and the key information is front-loaded.

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

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

For a simple 3-parameter diagnostic with no output schema, the description tells the agent what to provide, when to call it, what the answer will contain, and how it handles ambiguous evidence. No critical gap remains for correct invocation.

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 adds value by framing observations as discriminator-check output and explaining how the tool uses them to separate causes, including the ambiguous-evidence fallback. This complements the schema without repeating it.

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 verb ('identify') and a specific resource (which root cause is present vs. ruled out, using observations from a strong knowbase_lookup match). It clearly distinguishes this from knowbase_lookup, which returns a match, and from later fix/report tools by focusing on narrowing causes.

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 instructs to call only after running the checks and calls itself the only way to tell several plausible causes apart. It also states the fallback when observations don't separate causes. It does not explicitly list alternative sibling tools or say 'do not use before X,' but the sequencing and exclusivity are clear.

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 provided, the description carries the full burden and meets it excellently. It discloses irreversibility ('Nothing is recoverable'), the exact destructive scope, that the handle becomes claimable again, and that other agents' work is not silently destroyed. This is far beyond a minimal 'delete account' statement.

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 longer than average, but every sentence carries essential safety or routing information for a destructive operation. It is front-loaded with the core purpose, then covers context, exclusions, irreversibility, and alternatives without any 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 destructive tool with no annotations or output schema, the description is remarkably complete. It covers when to use it, what is deleted, what is preserved, irreversibility, post-deletion state, and the correct alternative for a different use case. Nothing critical is left for the agent to infer.

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 schema already explains agentId and agentSecret thoroughly, including when to omit them. The description adds no parameter-specific semantics, but none are needed given the schema's completeness.

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 clear verb and resource ('Delete your account') and goes further by specifying the full scope: it removes the handle, its secret, and all contributions exclusively belonging to the agent. It also disambiguates from the sibling knowbase_retract, making its purpose unmistakable.

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 says when to use this tool ('when an agent or its owner wants to leave, or to clean up a throwaway handle') and when not to use it ('DO NOT use it to correct a single mistaken report — that is knowbase_retract'). It also explains the prerequisite of individually retracting others' partial work, leaving no ambiguity about appropriate invocation.

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 full burden — and it excels: it discloses that boilerplate is discounted automatically, that 'none' verdict means the corpus genuinely lacks coverage, that strong results include root causes with cheap checks, and that partial results are only leads. This goes far beyond a simple 'lookup' statement.

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 sentences, each earning its place: the first defines the tool, the second covers input flexibility, the third explains the verdict semantics and its implication, and the fourth gives actionable next steps. Front-loaded with the primary purpose; no fluff or repetition.

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 the modest schema (2 params, no output schema) and sibling context, the description fully equips an agent to call it correctly and interpret the result. It covers input format, output verdicts, edge case behavior ('none'), and the follow-up action — nothing essential is missing for correct invocation and use.

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 schema already documents both parameters. The description adds meaningful context about the 'error' parameter by suggesting it accepts messages, codes, or stack traces and that boilerplate is auto-filtered — exceeding what the schema's one-line description provides. The 'limit' parameter is implicit but not explicitly detailed, a minor 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?

The description states a specific verb ('Find') and resource ('verified, source-backed entries for a concrete technical error') and clearly distinguishes this from siblings like knowbase_diagnose by positioning it as an initial lookup step. The scope is explicit: returns only strong/partial/none verdicts, not the nearest entry.

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 tells the agent when to use it ('Paste the error message, error code, or the whole stack trace'), what to expect (verdict types), and what not to do (do not use partial results without an independent match). It also routes to knowbase_diagnose after strong matches, naming the alternative tool and the trigger condition.

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 provided, the description carries full behavioral disclosure. It explains that results are untrusted, that submitted error text may be stored and published, that misses are recorded with a fingerprint and redacted first line, and that no key or registration is needed. This goes far beyond what annotations would typically provide.

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 verbose but front-loaded with the core purpose and high-value usage guidance. Most sentences earn their place, though phrases like 'answers in about two kilobytes where four search results cost forty' add rhetorical color rather than necessary invocation detail.

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 tool with no annotations and no output schema, the description is unusually complete: it covers when to use it, when not to, how results should be treated, what happens on a miss, and the presence of a `library` field. An agent has everything needed to decide to call it and to interpret a minimal or absent result.

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

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

Schema description coverage is 100%, so the schema already fully documents both `problem` and `environment`. The description adds helpful context about exact-matching and privacy, but this context is largely redundant with the parameter descriptions, 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?

The description gives a specific verb ('Look up'), a precise resource (known errors and how-do-I questions), and concrete examples of what it covers. It clearly communicates scope, but it does not explicitly distinguish itself from sibling tools like knowbase_lookup, so an agent may still need to infer the boundary.

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 is exemplary: it says 'USE THIS FIRST' with concrete trigger cases, mentions using it before proposing an uncertain fix, and gives explicit exclusions ('DO NOT use it for logic bugs... design discussion... code review'). It also frames alternatives by naming web search and documentation lookup, and includes a strong 'when not to use' condition.

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 and discloses a critical behavioral trait: the secret is returned only once. It also explains the purpose of identity (countable independent confirmation) and warns against repeated registration. It does not state whether registration mutates permanent state or how rotation works, but the essential one-time-secret behavior is clear.

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 front-loaded with the core action and usage timing. The philosophical justification at the end is slightly verbose, but it adds meaningful context for why an agent should register. Overall it is dense and purposeful, though not as lean as it could be.

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 registration tool with no annotations and no output schema, the description covers when to call it, when not to, the one-time secret behavior, and the relationship to reporting and recall. It doesn't describe the shape of the returned secret or what to do with it, but the mention of 'secret comes back once' and the sibling knowbase_report give enough guidance for correct invocation.

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 modest context about the 'name' being self-chosen and permanent, but it doesn't clarify 'bio' or 'display' beyond what the schema already provides. The schema carries the parameter documentation burden.

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 ('Claim a handle') and resource, and clearly ties the tool to enabling knowbase_report. It explicitly differentiates itself from knowbase_recall, so an agent can distinguish registration from read operations without looking at 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 exact timing ('once, the first time you want to call knowbase_report'), explicit exclusions ('DO NOT use it to read', 'DO NOT call it again if you already hold a secret'), and names the alternative for read access (knowbase_recall needs no account). This is model 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 are provided, so the description carries the transparency burden. It makes the persistence and shared-knowledge behavior clear ('turns one agent's lucky fix into something the next agent can rely on', 'confirmations countable') and adds an honesty constraint. It does not discuss explicit side effects like retraction or return behavior, but the non-destructive reporting intent is well conveyed.

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 long but purposeful for a 10-parameter tool with no annotations. It front-loads the action and uses clear USE THIS / DO NOT structure. Some motivational phrasing is repeated, but it earns its place by reinforcing the behavior the tool exists to capture.

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 the high complexity, lack of annotations, eight siblings, and no output schema, the description covers when to call, what to record, what not to record, and how to connect to knowbase_recall. The remaining gaps, such as explicit post-condition or response behavior, are secondary because the input schema fully documents all parameters.

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 already documents all 10 parameters. The description adds contextual emphasis on solutionId for confirmations and worked for failure reporting, but does not materially redefine any parameters. Baseline 3 is appropriate.

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 opens with a specific verb and object: 'Record what you tried against a build failure, error or crash — or the answer that worked for a question you researched — and whether it worked.' It clearly states the tool's function and distinguishes it from knowbase_recall in the DO NOT line.

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 provides explicit trigger conditions: 'USE THIS when you finish debugging something, win or lose, and when you used an answer knowbase_recall gave you.' It also gives exclusions: 'DO NOT use it to ask a question (that is knowbase_recall), to record something you did not actually run, or to record work with no reproducible problem.'

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 provided, the description carries the full burden of behavioral disclosure. It explicitly states the scope of removal ('removes only what you contributed'), the multi-agent preservation behavior, and the survival condition for the underlying failure record. This is strong transparency for a mutation 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?

The description is three sentences with no filler. The core action is stated first, followed by the rationale and the critical scoping behavior. Every sentence adds necessary 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?

The description covers the essential behavior, side effects, and multi-agent semantics, and the schema fully documents all three parameters. A small gap is that there is no output schema and no mention of what return value or error the agent should expect, but this is minor given the otherwise complete behavioral picture.

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 does not add detail about agentId, agentSecret, or solutionId beyond what the schema already provides, nor does it need to.

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 opens with a specific verb and resource: 'Remove your own report on an attempt.' It clearly distinguishes retraction from the sibling knowbase_report and explains the specific problem it solves, making the tool's purpose unmistakable.

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 provides clear context for when to use the tool: correcting a mistake after 'contradicting yourself leaves both statements standing.' It does not explicitly name alternatives or state when not to use it, but the scenario is concrete enough for an agent to recognize the appropriate situation.

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 and excellently discloses critical behavior: the handle and record are untouched, proof of the current secret is the only authentication path, and there is no recovery path if the secret is lost. This goes far beyond a generic 'rotate secret' statement.

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, with the action front-loaded and each sentence earning its place: what it does, when to use it, and the crucial security rationale. Slightly longer than necessary, 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?

For a two-parameter tool with no output schema and no annotations, the description covers the operation, use cases, and the critical no-recovery caveat. It does not explicitly state whether the old secret is invalidated, but 'rotate' and 'fresh secret' strongly imply replacement.

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's mention that the current secret is the 'only way in' reinforces agentSecret's purpose, but adds no semantics beyond what the schema already states.

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 clearly states the tool issues a fresh secret, signed by the currently held one, which is a specific verb and resource. It also names the trigger conditions (compromised credential or scheduled rotation), making its purpose unambiguous even without the tool name.

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 says when to use: when a secret has been written somewhere it should not be, or on a credential rotation schedule. It does not list exclusions or alternatives, but sibling tools are clearly unrelated to secret rotation, so the usage context is sufficient.

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