Atisbo

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

Annotations already establish readOnly=true and destructive=false, so the safety profile is covered. The description adds a behavioral output trait the annotations cannot convey: the result is a 'ready-to-render chart artifact' rather than raw data. It stops short of describing pagination or how over-large result sets behave, though the schema's cursor/limit descriptions partly cover that.

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 filler, and the highest-value information (what it does, when to use it first, and the alternative) is front-loaded. Nothing repeats the schema.

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 an output schema present, return values need not be explained, and the description covers dataset selection, filtering, grouping, metrics, and analysis kind at a high level. For a broad 9-parameter tool the only minor gap is guidance on combining group_by with metrics or the point at which pagination kicks in.

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 every parameter, enum, alias, and nesting rule is already documented in the schema. The description only paraphrases the parameter families ('time filters, grouping, metrics') without adding format, precedence, or defaulting detail. Baseline 3 applies when the schema does 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?

States a specific verb and scope: 'Broad analytical query over claims, solutions, or activity' and names the exact axes it covers (time filters, grouping, metrics, chart artifact). It explicitly contrasts itself with the sibling atisbo_lookup, so an agent can route between them 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?

Gives an explicit ordering rule ('Use FIRST for analytical questions spanning entities or time windows') and names the alternative plus the condition that selects it ('a single-entity drill-down is atisbo_lookup mode=get with the entity id'). Both the when and the when-not are 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?

The annotations already declare readOnlyHint=false and destructiveHint=true, so the safety profile is covered. The description adds little beyond those annotations: it says update/patch/add evidence, but does not disclose what gets overwritten, required change summaries, idempotency behavior, or other mutation consequences.

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 single sentence is concise and front-loads the main verb, but it is under-specified for a tool with 36 parameters and six core modes. The brevity is not matched by structure that would help an agent navigate the complex schema.

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 large nested schema, six required mode values, and destructive write behavior, the description is far too thin to be complete enough for correct invocation. Output schema and annotations cover some burden, but the description never explains the central mode routing or key mode-specific requirements.

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 description mentions none of the 36 parameters and does not clarify the required mode, change_summary, scope_id, or mode-specific fields. With schema coverage at 69% and several loosely documented or empty-schema parameters, the description does not compensate for the remaining ambiguity.

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 broad operations — capture signals/knowledge, update, patch, add evidence — but does not explain the six required mode values or distinguish among them. It gives a general sense of a multi-mode write tool without enough specificity to select the right mode or separate it from 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?

There is no when-to-use, when-not-to-use, or alternative-tool guidance. The description lists operations but leaves mode selection entirely to the schema, with no conditions for choosing between signal, knowledge, update_artefact, patch_artefact, or add_artefact_evidence.

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 declare destructiveHint=true and readOnlyHint=false, and the description adds meaningful nuance beyond them: delete is a 'soft-disconnect', the create secret is shown ONCE and must be relayed, and the tool only READS the connected system. These are non-obvious behaviors an agent needs. It doesn't cover rate-limit or failure semantics, so not 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 most important constraint (catalog is not the boundary) and the one-time-secret warning are front-loaded and emphatic. It is dense but each sentence carries operational weight; the all-caps emphasis is slightly noisy 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 an 18-parameter, multi-mode tool with an output schema and destructive annotations, the description covers the mode taxonomy and the key gotchas (fallback catalog, one-time secret, soft delete). Combined with the rich schema, an agent has enough to call it correctly, though mode-to-parameter mapping remains inferential.

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 18 parameters including mode enums and per-mode requirements. The description adds the mode vocabulary and which modes need ids, but no syntax or format detail beyond the schema. 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 tagline 'WHERE Atisbo gets its signals' plus the explicit mode list (list, catalog, create, configure, pause, resume, sync_now, delete) states a concrete resource and its operations, distinguishing it from siblings like atisbo_capture or atisbo_analyze. It is clear what the tool manages, though the opening metaphor is less literal than a plain verb+resource statement.

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

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

It gives actionable when-to-use guidance: call catalog and read `fallback` before declaring a source unsupported, and relay the one-time secret to the human immediately. It does not explicitly contrast against sibling tools (e.g., when to connect vs. capture), so it stops short of full routing guidance.

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

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

Annotations only give readOnlyHint=false and destructiveHint=true, so the description is carrying most of the behavioral burden. It discloses that writes require resolved UUIDs, that mutations self-log (so no separate log call is needed), and that declare_pm_exception escalates to a human. It stops short of flagging which specific modes are destructive (delete_solution, delete_claim, delete_knowledge) or what force/force_reassign confirmations guard against, which the schema describes only partially.

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 dense but well-organised paragraph: the facade framing is front-loaded, the three mode families are clearly labelled, and trailing sentences carry distinct constraints rather than filler. It is appropriately short for a tool whose detail lives in the mode enum and schema, though the ALL-CAPS families are a little compressed to parse.

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?

An output schema exists, so return values need not be explained, and the description correctly points elsewhere ('notes per mode in meta.guidance'). But for a 27-mode, 74-parameter mutation tool with destructiveHint=true, the description is thin: no mode-level detail, no prerequisite/permission context, and no warning about which operations are irreversible. It is minimally viable rather than 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?

With 74 parameters and only 58% schema description coverage, the description would need to compensate, and it mostly does not. It adds two genuine semantic rules ('writes require UUIDs', 'log_decision only for external decisions'), but the schema's per-mode parameter tagging (e.g. 'record_outcome: launch impact') does the real work. Baseline 3 for a schema that is doing the heavy lifting while the description adds marginal value.

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 concrete framing ('PM decision facade') and groups the 27 modes into three labelled families (CURATE, EXECUTE, DOCUMENT/GOVERN), so an agent can tell roughly what the tool owns. However it never names or contrasts the sibling tools (atisbo_capture, atisbo_analyze, atisbo_lookup), so the boundary between this facade and the rest of the surface is left to inference.

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 does supply real routing rules — 'log_decision is only for external decisions; mutations log themselves' and 'mode=declare_pm_exception marks a CLAIM as needing a human decision' — which are genuine when-to-use signals. But there is no guidance on choosing this tool over its siblings, nor on which of the 27 modes to pick for a given intent; usage is implied by the mode enum 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?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description only gestures vaguely at return content ("snippet text + attachment URLs, queues, outcomes") which overlaps the existing output schema, adding no auth, rate-limit, or mutation-recovery context.

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 the verb front-loaded and no wasted words. But the second sentence is a comma-spliced grab-bag that is too terse to organize a 20-mode, 40-parameter surface, so it reads as under-specified rather than efficient.

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 20 modes and 40 parameters, the description omits the mode taxonomy almost entirely, forcing the agent to infer behavior from enum values alone. Even with a rich output schema, the missing mode-level routing guidance leaves a significant gap.

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

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

Schema description coverage is 95%, so the schema already documents nearly every parameter thoroughly (including cross-tool hints like "resolve names with atisbo_lookup mode=resolve first"). The description adds no parameter 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?

The description states a verb+resource ("Find or open Atisbo entities") and lists content types modes can expose. However, with 20 modes ranging from `open` to `receipts`, the purpose is sprawling and the description does nothing to distinguish this tool from siblings like atisbo_orient or atisbo_analyze.

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 when-to-use guidance appears in the description; it defers entirely to "notes per mode in meta.guidance," an external reference the agent may not have. Nothing tells the agent which of the 20 modes to pick or when to prefer this tool over atisbo_orient/atisbo_analyze.

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 destructiveHint=true, so the safety profile is known; the description then adds mode-level behavioral constraints ('refuses non-taxonomy maps', 'refuses taxonomy maps'). However, it never says which modes are destructive (delete, regroup, sync_claim_snipes) or what data is lost, leaving a meaningful gap for a destructive multi-mode 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?

Two tightly packed sentences, front-loaded with the facade scope and followed by the single highest-risk disambiguation. Every clause maps to a distinct capability or constraint; nothing is 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?

Output schema exists, so return values need no explanation, and the description plus meta.guidance pointer covers the mode-driven surface. Completeness is slightly reduced because the bulk of per-mode semantics is deferred to meta.guidance rather than stated here, and destructive scope remains unstated.

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?

With 42 parameters at 62% schema coverage, the description must carry weight, and it does: it explains the required mode parameter's routing intent, disambiguates anchor vs link_claims semantics, and flags preview-first and mode=apply preference. It does not cover the many other mode-specific parameters, so it stops short of full compensation.

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 names specific verbs and resources (create/apply maps, generate/edit nodes and edges, anchor claims/snippets, bind metrics, regroup) and explicitly frames the tool as a 'map facade', which cleanly separates it from the analyze/decide/capture siblings. An agent immediately knows this is the map-mutation surface.

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?

Adds real routing guidance: 'Prefer mode=apply for full MECE categorization' and a precise when-to-use-which rule for mode=anchor vs mode=link_claims, including the refusal conditions (non-taxonomy vs taxonomy maps). It does not route among all 17 modes or vs atisbo_connect for edges, so it falls short of a 5.

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 destructiveHint=false, so the safety profile is covered and not contradicted. The description adds the workflow-continuity rule and the snippet:// reference convention, but says nothing about pagination behavior or what the four modes actually yield beyond the schema's own mode list.

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 the purpose and the mode list before the routing rules, and no sentence is redundant. It is dense with cross-tool references, but each clause carries routing 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?

With annotations, a full output schema, and 100% parameter coverage handled elsewhere, the description only needs to supply the routing map, which it does. Minor gap: the cursor/pagination behavior and the relationship between orient and atisbo_map are left implicit.

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 every enum (mode, task, depth) is documented inline, so the schema does the heavy lifting. The description simply repeats the mode names already enumerated in the schema and adds no syntax, defaults, or interaction detail beyond it — 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 the resource (workspace) and enumerates the four modes, giving operational sense, but the verb 'orientation' is vague and borders on restating the tool name. Sibling differentiation is partial: it names atisbo_lookup, atisbo_analyze, and atisbo_capture for adjacent tasks, which implicitly scopes what orient is not, yet it never plainly says what orient returns.

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 rule 'Continue the user's existing workflow; never create a parallel backlog' is a genuine usage constraint, and the routing sentences point to other tools for opening docs, corpus reads, and edits. However, there is no explicit statement of when to choose orient over siblings like atisbo_map or atisbo_analyze, only a description of what those siblings do.

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 description adds real behavioral context the annotations do not carry: which subsystems are checked (integrations, ingestion, clustering, gates, key scope), that the result is a playbook, that diagnostics cannot see the failed call, and that `problem` is filed verbatim in a report. However, it also discloses that share_report files a report — a state-changing side effect — while the annotations declare readOnlyHint=true, so an agent trusting the annotation alone could be misled.

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 the verb and the concrete failure phrasings, then routing, then privacy constraints — good information ordering with almost no filler. It is dense to the point of reading as a run-on, but 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?

An output schema exists, so return values need not be explained, and all four parameters are fully documented in the schema. What the description must add — scope of checks, privacy caveats, sibling routing — it delivers, leaving no gap an agent needs to resolve before calling.

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 goes further for the highest-risk parameter by warning that `problem` is filed and must not contain customer feedback, document bodies or credentials, and that `observed_error` is often the only evidence. That is meaning beyond the schema's type/length constraints.

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 ("Diagnose Atisbo") and concretizes it with three quoted failure phrasings that map directly to the tool's job. It also names the sibling it is not ("Use atisbo_lookup/atisbo_analyze for backlog"), so an agent can separate it from the other seven atisbo_* tools 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?

Gives explicit trigger situations ("I connected a source and nothing appeared", "my data is missing") and names alternative siblings for the non-diagnostic case. It also tells the agent it can omit `area` when unsure, which is a concrete invocation decision, not just a hint.

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