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

No annotations provided, so description must disclose behaviors. Only states 'return' and 'live,' implying read-only, but no mention of side effects, permissions, error conditions, or uniqueness guarantees.

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?

Single 9-word sentence is concise and front-loaded. However, extreme brevity sacrifices clarity on parameters and usage.

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 having an output schema and 4 parameters, description omits return value context and parameter semantics. Complexity is high relative to the minimal description, leaving gaps for effective tool 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 0%, yet description gives no parameter details. It loosely mentions 'stable topic key' but doesn't explain 'repo,' 'scope,' or 'client.' Agents cannot infer correct usage from description.

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?

Description clearly states 'Return the one live decision for a stable topic key,' specifying verb, resource, and scope. It distinguishes from siblings like 'recall_decisions' (likely returns multiple) and 'record_decision' (create).

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?

Implies usage for stable topic keys, but no explicit when-to-use or when-not-to-use guidance. Lacks comparison to siblings like 'why' or 'decisions_as_of'.

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 are absent, so the description must compensate, but it only states the basic action. It does not disclose read-only nature, permissions, empty chain handling, or ordering implications beyond 'oldest-to-newest'.

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?

Single sentence that efficiently conveys the core functionality. Front-loaded with action and scope, no filler.

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

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

For a simple read tool with one parameter and an output schema, the description covers the main idea but lacks parameter explanation and context about the chain structure. Adequate but incomplete.

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 parameter 'uuid' has 0% schema description coverage. The description mentions 'a decision' but does not clarify that uuid identifies the decision, nor does it specify format or constraints. Minimal added meaning.

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 verb 'show' and the resource 'supersession chain' for a decision. It distinguishes the tool from siblings like 'current_decision' (shows current only) and 'supersede_decision' (creates a supersession), making the lineage intent unique.

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 guidance on when to use this tool versus alternatives such as 'why', 'current_decision', or 'supersede_decision'. There is no explicit context for selection or exclusion.

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 must disclose behavior. It only states the core function (returning historical decisions) but omits safety, permissions, side effects, or what 'effective' means. Minimal behavioral disclosure.

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

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

One concise sentence. However, it is under-specified for a 3-parameter tool. Conciseness is good for the purpose, but missing parameter details lowers effectiveness.

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 3 parameters, no annotations, and an output schema, the description is incomplete. Does not explain return value or usage context, leaving gaps for an 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 has 0% description coverage. The description only implies 'as_of' is the historical time point but does not explain 'limit' or 'decision_key'. Fails to compensate for missing schema descriptions.

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 it returns decisions effective at a historical point in time. This distinguishes it from siblings like 'current_decision' but does not explicitly name alternatives.

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 guidance on when to use this tool versus alternatives like 'current_decision' or 'recall_decisions'. Lacks context on prerequisites or exclusions.

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

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

No annotations provided. Description adds temporal validity note about invalid_at dates, which is a behavioral trait. However, it does not disclose other traits like read-only nature, permissions, or result format. With no annotations, the description carries burden but only partially fulfills it.

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?

Description is relatively concise with two sentences plus a critical note on temporal validity. It front-loads the purpose and use case efficiently, though the note could be integrated more smoothly.

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 presence of an output schema (not shown) and sibling tools, the description provides adequate context for core purpose and usage guidelines. However, it lacks parameter details and more thorough behavioral transparency, leaving gaps for a complete understanding.

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% and description does not explain parameters. While 'query' and 'limit' are intuitive, the description adds no guidance on their usage, formats, or constraints. For a tool with no parameter descriptions in schema, this is a notable 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?

Description clearly states the tool searches meeting transcripts for client/stakeholder statements. It differentiates from siblings like recall_decisions by focusing on 'context' rather than decisions. Verb 'search' and resource 'meeting transcripts' are specific.

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 when to use: to find origins of asks, promises, or requirements before acting on second-hand info. Does not specify when not to use or list alternatives, but the context 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?

No annotations provided, so description must cover behavioral traits. It implies a read-only search but does not explicitly state idempotency, side effects, or permissions. Adequate for a simple search tool but not rich in transparency.

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 concise sentences; first sentence states purpose, next two provide usage guidance. No redundancy, every sentence 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?

Given multiple sibling tools and an output schema, the description omits parameter explanations and usage comparisons. It gives a clear call-to-action but lacks full context for an agent to use it confidently.

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%, and the description adds no parameter-level details (e.g., what query means, how limit works, or the effect of include_superseded). It barely adds meaning beyond the schema's bare names.

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 verb (search) and resource (prior architectural decisions), and the context about superseded decisions distinguishes it from sibling tools like record_decision or current_decision.

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 to call before non-trivial design, and highlights superseded/rejected decisions as valuable. However, it does not discuss when not to use or compare to siblings like recall_context or why.

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 present, so the description must convey behavior. It adds useful context for decision_key (stable kebab-case), decided_at (effective date), and scope (repo/client/practice), but omits critical behaviors like whether duplicate keys overwrite, required permissions, or side effects (e.g., creation vs. update). The description is partially transparent but insufficient 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 concise (4 sentences) with the main purpose front-loaded. The bullet-like clarifications for decision_key, decided_at, and scope are efficient. However, additional structure (e.g., grouping parameters) could improve scannability.

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 having an output schema (not shown), the description does not explain the return value, error conditions, or how to use all 10 parameters. Given the tool's moderate complexity and missing schema descriptions, the description leaves significant gaps for the agent.

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. It explains only 3 of 10 parameters (decision_key, decided_at, scope), leaving repo, client, statement, rationale, source, session_id, and alternatives_rejected undocummented. This partial coverage fails to guide an agent on the majority of inputs.

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's purpose with a specific verb ('Record') and resource ('settled architectural decision'), and distinguishes it from sibling tools like recall_decisions or supersede_decision by focusing on creation rather than retrieval or modification. The purpose is unambiguous and action-oriented.

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 implies usage for persisting decisions to avoid re-litigation, but does not explicitly contrast with sibling tools (e.g., when to use this vs. supersede_decision or decisions_as_of). No 'when not to use' guidance is provided, leaving the agent to infer context from the name alone.

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?

Discloses that the old decision becomes 'REJECTED history', a key side effect. However, given no annotations, more details (e.g., permissions, irreversibility) would improve transparency.

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 concise sentence that front-loads the action. It is efficient, though it could be expanded slightly to include parameter hints without losing brevity.

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 having an output schema and multiple sibling tools, the description lacks parameter guidance, usage context, and behavioral details. Significant gaps remain for an agent to use it 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 description coverage is 0%, and the description does not explain any parameter. The agent must infer meaning from parameter names alone, which is insufficient.

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 it retires a decision and replaces it, preserving the old one as rejected. This distinguishes it from sibling tools like record_decision (create) and current_decision (read).

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 explicit guidance on when to use this tool versus alternatives. The purpose implies replacement, but no contrasts to siblings are provided.

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

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

No annotations provided, so description carries full burden. It states returns 'dated, speaker-attributed excerpts', which is useful but doesn't disclose potential side effects, auth needs, or performance. Read-like behavior implied but not explicit.

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

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

Three sentences, front-loaded with purpose, then usage, then return info. No redundant words. Highly 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?

Given output schema exists but not detailed here, description covers return structure adequately. However, missing parameter documentation is a gap for a simple 2-param 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 description coverage is 0%. The description does not explain 'topic' or 'limit' parameters. 'Topic' is implied but not defined, and 'limit' is not mentioned. Agent likely needs more guidance on what 'topic' refers 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?

Description clearly states the verb 'Explain why' and resource 'a decision exists', adding 'quoting the client conversation'. It distinguishes from siblings like 'recall_context' and 'recall_decisions' by focusing on justification and quotes.

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 lists three scenarios for use: when a constraint looks arbitrary, when arguing against a decision, or when the user asks for a requirement's origin. No explicit when-not-to-use, but context is clear.

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