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

Annotations cover safety (readOnly/idempotent/non-destructive), and the description goes well beyond them: empty-bin back-filling for COUNT/UCOUNT (filled_empty_bins), SAMPLE returning one example event and no spikes, the 2-sigma spike rule, the <3-bin/flat-series exception, and the warning that an empty 'spikes' list is not evidence of calm. These are exactly the behavioral traits 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 the action, then labeled WHEN and RETURNS sections, so it is easy to scan. It is long, but with no output schema the return-shape detail and spike caveats earn their space; only mild trimming would be possible.

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?

Despite no output schema, the RETURNS block fully describes the response shape (bins, spikes, note, SAMPLE variant), and window/field/aggregation semantics plus edge cases are covered. Nothing needed to invoke or interpret the result 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 every parameter is already documented in the schema. The description restates some of that (e.g., COUNT being the aggregation spike detection runs on, bin_width_ms resolution trade-offs), adding reinforcement rather than new meaning. Baseline 3 is appropriate since the schema carries the parameter load.

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 ('Aggregate matching events into a time series and detect spikes') and immediately contrasts with the raw-event sibling via 'without pulling raw events' and 'Follow up with search_logs'. An agent can route between aggregate_logs and search_logs without opening either 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?

The WHEN block names the intended use case (find whether/where log volume burst) and explicitly names the alternative (search_logs on the spike window) with the condition that selects it. The boundary between aggregating and pulling raw events is spelled out rather than inferred.

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

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered; the description adds real value with the return projection ({id, name, enabled, info} plus raw_keys) and how raw_keys exposes previously unseen fields. It does not need to restate 'Read-only' since annotations carry that, but the return-shape disclosure is substantive.

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 a [READ] tag and the core action, then supporting detail. Every sentence carries information (routing, return shape, raw_keys rationale), though the closing 'Read-only.' slightly duplicates the annotation.

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 describes what comes back, including raw_keys, so an agent knows the response shape. Combined with the thorough schema error descriptions, the definition is nearly complete for a simple two-parameter read.

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 target and alert_id are fully documented in the schema, including error behavior (404/500, malformed-id refusal). The description adds no parameter-level detail beyond the schema, 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 ('Get the stored definition of one alert') and names the sibling it follows from (list_log_alerts). It is clearly distinguishable from get_log_alert_history, which it explicitly routes to for firing data.

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 sequencing guidance ('Use this after list_log_alerts') and names the alternative for a different question ('For when the alert fired, use get_log_alert_history'). Both when-to-use and when-to-use-something-else are covered.

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 cover readOnly/idempotent/destructive, yet the description still adds substantial non-obvious behavior: the exact return envelope {items, returned, limit, total, truncated, hint}, the fact that each item carries at most 3 events, and the paging rule that a full page yields total null and truncated true. That is exactly the kind of context annotations cannot express.

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 discriminating clause before the return-shape detail. It is dense and long-ish, but nearly every sentence carries information an agent needs (envelope shape, 3-event cap, pagination behavior); only the '(verified on 8.18.7)' asides are mild 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?

There is no output schema, so the description must carry the return contract — and it does, including item fields, the messages sub-array, empty-list behavior, and truncation semantics. Combined with 100% parameter coverage, an agent has everything needed to call and interpret this tool.

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

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

Schema coverage is 100%, so the baseline is 3, but the description adds interpretive meaning for limit that the schema alone doesn't: it explains how to read total/truncated relative to page size and implies the limit bounds how much history is reachable. The alert_id and target semantics 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: 'List recent trigger-history records for an alert.' It also explicitly scopes itself against the definition-oriented sibling with 'Use this for when an alert fired, not how it's defined,' so an agent can separate it from get_log_alert/list_log_alerts without opening schemas.

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 when-to-use guidance ('when an alert fired, not how it's defined') plus an edge-case rule: an alert that never fired returns an empty list, not an error. It stops short of naming the alternative tool explicitly (get_log_alert) or stating when-not to call it, so it is clear context without full routing.

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

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so '[READ]'/'Read-only' adds little beyond structured data. However, the description does add genuine value: with no output schema present, it discloses the return shape {version, release_name, build} and the diagnostic intent, which goes beyond the annotations.

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 purpose, then return shape, then usage — a sensible ordering with no filler sentences. The trailing 'Read-only.' and the '[READ]' prefix duplicate the annotations and each other, a small redundancy against an otherwise tight description.

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-required-parameter, single-parameter read tool with no output schema, the description covers purpose, return fields, and when to reach for it. It is essentially complete; only minor details (e.g., whether the call requires working credentials in all cases) are left to the schema.

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 'target' parameter is thoroughly documented in the schema itself (config file location, default_target fallback, error behavior, credential check). The description adds nothing about the parameter, so the 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?

States a specific verb and resource ('Return the Log Insight appliance version/build') plus the diagnostic purpose, and explicitly differentiates from siblings by naming search_logs as the query tool this one supports. The agent can tell immediately this is a version/metadata lookup, not a log search.

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 a concrete trigger condition ('Use this first when a query behaves unexpectedly... to confirm the appliance version before trusting search_logs') and names the sibling it complements. It stops short of explicit when-not-to-use guidance (e.g., avoiding it for routine log retrieval), so it is clear context but not a full routing rule.

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

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

Annotations already declare readOnly, idempotent, non-destructive, but the description adds real context beyond them: the exact return envelope shape ({items, returned, limit, total, truncated, hint}), the per-item fields, and the meaning of total/truncated for pagination. The read-only restatement is redundant with annotations but harmless reinforcement.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the purpose, then the return shape, then the routing advice, in four compact sentences. Slight redundancy between the description's envelope details and the schema's limit description, but nothing is wasted or buried.

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 fully carries the burden by documenting the envelope, item shape, and truncation semantics, and the schema covers target defaults and filter behavior. An agent has everything needed to call and interpret this correctly.

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

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

Schema coverage is 100%, so the baseline is 3; the description goes further by tying limit and name_filter together behaviorally — total reflects all matches after name_filter, small limits don't hide the count, and filtering happens locally on the full collection. That is useful action-level meaning beyond the parameter definitions.

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 defined Log Insight alerts' — and immediately distinguishes itself from siblings by naming get_log_alert and get_log_alert_history as the follow-on calls. An agent knows this is the enumeration entry point without opening any 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 clear routing guidance ('Start here, then pass an id to get_log_alert or get_log_alert_history') and a concrete follow-up rule for the truncated case (raise limit or narrow name_filter). It does not explicitly say when not to use it (e.g., versus search_logs/aggregate_logs for log events rather than alert definitions), so it stops short of full when/when-not coverage.

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 readOnly/idempotent annotations, it discloses the exact return envelope shape, item structure, the content-pack qualification rule, the 'unresolved' failure mode, and the cardinality cost (~340 fields, ~15k tokens) with the mitigation (pass name_filter). This is unusually rich behavioral 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?

Dense but front-loaded: the purpose sentence comes first, then usage, then return shape and caveats. Nearly every sentence earns its place, though the return-envelope detail is somewhat lengthy given no output schema exists.

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-format burden and does so fully (envelope fields, item fields, edge cases). For a 2-param read tool with rich annotations, nothing an agent needs to call 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 coverage is 100%, so a 3 is the baseline; the description adds real value by explaining that name_filter matches the qualified content-pack name and that omission returns everything, plus the practical warning to use it. It adds meaning beyond the schema text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb+resource ('[READ] List the fields this appliance knows') and immediately scopes it as static and extracted. It clearly distinguishes itself from siblings by naming what it feeds (aggregate_logs) and what it explains (search_logs 'fields').

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?

States two concrete use cases: picking a 'field' value for aggregate_logs, and interpreting a key in a search_logs event's 'fields'. Names the sibling tools explicitly so the agent can route without opening schemas.

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

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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint=false, and the description adds substantial context beyond them: truncation signalled by 'complete', a 'note' when limit was lowered, whole-word CONTAINS matching semantics with wildcard behavior, the absence of a field-filter parameter, and ValueError on malformed windows. This is exactly the extra behavioral detail the annotations cannot carry.

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 a [READ] tag and WHEN/RETURNS headings; each sentence carries load. The RETURNS block is long but justified because no output schema exists to carry that 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?

With no output schema, the description fully specifies the return shape (count, complete, constraints, events with timestamp_ms/text/fields), explains the fields dict contents and the content-pack exclusion, and warns about token cost. Nothing needed to call or interpret the result 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 the rich per-parameter docs (window formats, mutual exclusion, epoch-vs-seconds) are already in the schema and the description earns no extra credit for them. The description adds only the meta-point that there is no field-filter parameter. 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?

States a specific verb and resource ('Search Log Insight events within a time window') and explicitly differentiates from siblings by naming aggregate_logs for burst questions and vmware-monitor for vCenter alarms. An agent can route correctly without opening any 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?

The WHEN section gives a concrete use case ('find the actual log lines behind an incident') plus explicit when-not conditions pointing to two named alternatives. It also names a downstream consumer (vmware-debug build_incident_timeline), so the agent knows how this tool fits a workflow.

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