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

No annotations are provided, so the description carries the full burden. It does add one meaningful behavioral fact beyond the schema: only *approved* drafts are returned, implying unapproved ones are filtered out. It says nothing about ordering, pagination, or how the limit truncates results, which is a notable omission for a read tool with no annotation coverage.

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 resource and scope appear before the purpose. It is efficient, though arguably too terse given the documentation gaps it leaves behind.

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-value explanation is not required. However, with zero schema coverage, no annotations, and an undefined `limit` default of 2, the description is too thin for an agent to know what it will receive or how results are bounded.

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 0% across three parameters. The phrase 'instance/request pair' loosely maps to instance_id and request_id, but the `limit` parameter (with default 2) is never explained in either the schema or the description, so the description fails to compensate for the coverage gap.

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

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

States a specific verb (read) and resource (approved drafts) scoped to an instance/request pair, with the intent (historical context) made explicit. It is distinguishable from siblings like get_instance_summary or get_timeline by the 'approved drafts' resource, though it never names an alternative directly.

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?

'as historical context' implies the situation that motivates the call (looking for precedent), but there is no explicit when-to-use, when-not-to-use, or guidance on choosing this over get_instance_summary/get_timeline. 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?

No annotations are provided, so the description carries the full behavioral burden. The word "only" hints at a scoped subset of data, but there is no disclosure of permissions, rate limits, or how incomplete data is handled, and no output schema is needed here but the description still says nothing useful about behavior.

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

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

One short, front-loaded sentence with no wasted words, but its brevity reflects under-specification rather than efficient communication.

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 needn't be explained, and there are no annotations to contradict. Still, for a read tool with two undocumented params, the description leaves an agent guessing what it actually retrieves and when it applies.

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 0%, so the description is the only source of parameter meaning. It names the "instance/request pair," which loosely maps to the two required params, but adds no format, ID provenance, or 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?

The description states a verb ("Return") and a scope (specific instance/request pair), but "signals" is undefined and does not match the tool name's promise of an "instance summary." It does not distinguish this tool from siblings like get_timeline or get_case_memory.

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 is given. It never says when to prefer this over get_timeline or get_case_memory, nor what preconditions (e.g., a known request_id) must hold.

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

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

With no annotations, the description carries the full burden. It usefully discloses that results are bounded and limited to opening and terminal events rather than a full event list, but it omits read-only confirmation, pagination behavior, and how the limit parameter affects the result.

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 a single front-loaded sentence with no filler. However, its brevity contributes to ambiguity around what 'bounded' and 'specified operation' mean in practice.

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 output schema may cover return values, but the input schema has 0% description coverage and there are no annotations. For a three-parameter tool, the description leaves key invocation details and behavioral expectations undocumented.

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 0% for three parameters, and the description does not explain instance_id, request_id, or limit. The phrase 'specified operation' hints at request_id but does not provide enough semantic detail to compensate for the schema 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 gives a specific verb ('Return') and resource scope ('opening and terminal events of the specified operation'). It is clear enough to distinguish from generic log/search tools, though it does not explicitly name or differentiate itself from any sibling tool.

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

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

There is no guidance on when to use this tool versus alternatives such as search_logs or get_instance_summary. It implies the tool is for inspecting an operation's events, but offers no conditions, exclusions, or prerequisites.

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 full burden. It usefully discloses the approval gate and the persistence backend, but omits what happens when approved=false (no-op vs. error), permission requirements, and whether saving a draft is idempotent or overwrites an existing draft.

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 gating condition is stated as part of the core purpose rather than 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?

For a mutation tool with no annotations, a required nested-object parameter, and 0% schema coverage, the description is too thin — an agent knows the gate but not the ticket payload shape or failure behavior. The existing output schema removes the need to explain return values, but that alone doesn't close the 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 coverage is 0% and one parameter, ticket, is an unconstrained object (additionalProperties: true) with no description anywhere — the description does not hint at what fields a valid ticket must contain. It only clarifies approved's effect, meaning the more complex required parameter remains entirely undocumented.

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 (persist), resource (a draft), and storage target (PostgreSQL), which no sibling tool overlaps with — all siblings are read/inspection tools. An agent can immediately tell this is the sole write path for drafts.

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 gating condition: persist only when the caller passes approved=true, which effectively tells the agent when this tool will act. It stops short of naming alternatives or describing what to do instead when approved is false (skip the call? use another tool?).

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, but it does add two real behavioral facts: reads are bounded to 100 results, and evaluation labels are never exposed (a useful data-disclosure guarantee). It omits ordering, pagination/truncation behavior, error behavior, and permission requirements, so it is only partially transparent.

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, front-loaded sentences with no filler; the scope constraint and the data-exposure guarantee are each stated once. Nothing could be trimmed without losing content.

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 shape need not be explained, but for a 5-parameter search tool with zero schema descriptions and no annotations, the description leaves filtering semantics, required-identifier usage, and sibling routing entirely unspecified.

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 0% across 5 parameters. The description only obliquely touches the limit parameter by implying a ceiling of 100 (schema default 30), and says nothing about query, levels, request_id, or instance_id semantics. This does not compensate for the undocumented 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 description states the verb and resource ("Read ... matching logs") and a hard cap of 100, so the basic action is clear. However, it never says what the logs are matched against, nor does it distinguish this from siblings like get_timeline or search_runbooks that an agent could plausibly reach for instead.

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 guidance at all: no indication of when search_logs is preferred over get_timeline, get_instance_summary, or search_runbooks, and no mention of prerequisites such as requiring an instance_id and request_id. The agent must infer routing purely from the name.

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 full burden. It discloses a key semantic trait—that results are guidance, not evidence—which is valuable. However, it doesn't mention return format (despite an output schema existing), pagination, or authentication requirements.

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 extremely concise—just two clauses—and front-loaded with the core action. It could be slightly more informative without becoming verbose, but it avoids waste.

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 zero schema description coverage, no annotations, and the presence of an output schema, the description is incomplete. It does not explain parameters, return structure, or differentiate from siblings, leaving the agent with insufficient information to call the tool correctly in context.

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

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

Schema description coverage is 0%, so the description must compensate for undocumented parameters. It mentions no parameter details; 'query' and 'limit' are not explained in the description. The phrase 'citeable chunks' implies a chunked return but does not clarify query behavior or limit semantics.

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

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

The description states a retrieval intent ('Find citeable Runbook chunks') but the phrasing is terse and domain-specific. 'Citeable' and 'Runbook chunks' are jargon that an agent may not disambiguate without prior context. It doesn't clearly distinguish itself from sibling search_logs beyond the resource 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?

The only usage hint is the caveat 'guidance is not incident evidence,' which implies a negative use-case (don't use as evidence) but offers no positive guidance on when to prefer this tool over search_logs or get_case_memory. There are no explicit alternatives or conditions.

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

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

With no annotations, the description carries the full behavioral burden and provides almost none of it: no side effects, no permission requirements, no statement of what happens on mismatch, no indication whether this is a read-only check or a mutating operation. Only the matching condition is 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 with no filler; the action and its scope come first. It is efficient, though arguably too terse to be fully self-sufficient.

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, which lowers the bar. Still, for a validation tool with zero annotation and zero schema-description coverage, the definition leaves the semantics of a 'match' and the failure behavior 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?

Schema description coverage is 0% with three required parameters, so the description must compensate. It does map loosely onto all three params (citations, instance, request), but adds no format or syntax detail — e.g., what a citation string looks like or how instance_id/request_id relate to it. Partial compensation only.

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 ('Verify') and resource ('citations') plus the scope conditions (match the investigated instance and request). No sibling in the list performs validation, so differentiation is implicit rather than stated. Clear, but not maximally sharp about what a 'match' entails.

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

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

There is no explicit when-to-use, when-not-to-use, or alternative-tool guidance. Usage can only be inferred from the purpose sentence (i.e., call it when you have citations to check). No routing information relative to siblings like get_instance_summary or get_timeline.

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