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

With no annotations, the description should disclose behavioral traits. It states basic functionality (returning a session) but does not mention that it is read-only, any permissions needed, or behavior on missing session_id. Minimal but acceptable for a simple getter.

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, well-structured sentence that front-loads the purpose and uses no unnecessary words. Every part is essential.

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 simplicity (one optional parameter, no output schema), the description covers the essential behavior. It could mention that the tool does not modify data, but that is implied by 'Return'.

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 compensates by explaining that omitting session_id returns the active session while providing it returns a specific record. This adds significant meaning beyond the bare 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 clearly states it returns a session record, either the active one or a specific one by ID. It distinguishes the retrieval purpose from sibling tools like 'record_decision' or 'update_state', but could be more explicit about overlap with other getters like 'get_state'.

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 is provided on when to use this tool versus alternatives like 'get_state' or 'get_task_context'. The description does not specify prerequisites or exclusions, leaving the agent to infer without context.

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 convey behavioral traits. It implies a read-only operation by using 'return', but does not explicitly state idempotency, authorization needs, or performance implications. Adequate for a simple read, but not thorough.

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 description is concise and front-loaded with action and resource. It could benefit from a slight expansion on output format, but remains 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 no output schema, the description should explain what the return includes. It mentions 'summary and record counts', which is helpful but vague. With sibling tools having more specific focuses, a bit more clarity would aid completeness.

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?

No parameters exist, so schema coverage is 100% by default. According to guidelines, baseline is 4 for zero parameters. No additional explanation needed.

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 a 'project state summary and record counts', which identifies the specific resource and action. However, it does not explicitly distinguish from sibling tools like get_task_context or search_state, though the mention of 'summary' implies high-level overview.

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 provided on when to use this tool versus alternatives (e.g., get_task_context, search_state). The description lacks any contextual cues for selection.

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?

Without annotations, the description bears full responsibility for disclosing behavior. It implies read-only access via 'return' but does not confirm safety, error handling, or what constitutes 'compact' state. Critical traits like idempotency or side effects are omitted.

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, well-formed sentence. It is concise but arguably too brief—adding one more sentence about parameters or return format would improve informativeness without sacrificing 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?

Given the lack of annotations, output schema, and parameter descriptions, the tool is incompletely specified. A simple two-parameter retrieval tool should document parameter roles and return value nature to ensure 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 0%, and the description adds no meaning to the parameters 'task' or 'limit'. The agent cannot infer what 'task' qualifies as an identifier or how 'limit' affects the result (e.g., max number of items).

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 returns 'compact decision-relevant state for a specific task,' which indicates a focused retrieval operation. It distinguishes from siblings like 'get_session' and 'get_state' by specifying task-specific scope, but does not explicitly contrast them.

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 no guidance on when to use this tool versus alternatives like 'get_session' or 'get_state'. There is no mention of preconditions, scenarios, or exclusions, leaving the agent to infer usage from the tool 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?

No annotations provided, so description carries full burden. It only mentions 'persist' and 'update recent_decisions' without disclosing side effects, permissions, or limits. The tool creates a record, but implications for session state or data integrity are unclear.

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 is concise and front-loaded, but given the tool's complexity, it is under-specified. Not every sentence earns its place because there is only one sentence.

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?

Tool has 10 parameters, nested objects, no output schema, and no annotations. The minimal description does not provide enough context for an AI agent to use it correctly, especially for optional fields like 'evidence' and 'tradeoffs'.

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?

Description adds no meaning to any of the 10 parameters; it does not explain fields like 'evidence_context' or 'tradeoffs'. Schema coverage is 0%. For a tool with nested objects, this 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?

Description clearly states the action ('Persist') and resource ('structured decision'), and mentions the side effect of updating recent_decisions. This distinguishes it from siblings like 'record_evidence' or 'reflect_outcome'.

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. Sibling tools like 'record_evidence' and 'reflect_outcome' suggest different purposes, but the description does not clarify when one is preferred.

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 must convey behavioral traits. It only says 'persist', implying a write operation, but does not disclose side effects (e.g., overwriting, idempotency), authorization needs, or performance implications.

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 short sentence, which is concise but underspecified for a tool with 7 parameters. It lacks structure (e.g., no separate sections) and does not front-load critical information effectively.

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 has 7 parameters, no output schema, and no annotations, the description is insufficient. It fails to explain the tool's usage, expected output, or behavior for key parameters like 'session_id' and 'tags'.

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%, meaning the input schema provides no parameter documentation. The description mentions 'sources, findings, limitations, and confidence' which correspond to some parameters, but does not explain their semantics, expected formats, or relationships (e.g., optionality, 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 clearly states the action ('persist') and the resource ('normalized evidence sources, findings, limitations, and confidence'), providing a specific purpose. However, it does not explicitly differentiate from sibling tools like 'record_decision', which also records 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?

No guidance on when to use this tool over alternatives (e.g., record_decision, reflect_outcome). No context about prerequisites or scenarios where this tool is appropriate or inappropriate.

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. The description merely states 'Record the outcome...' without disclosing behavioral traits such as whether the tool creates a new record, updates existing data, requires authentication, or has side effects. This is insufficient for a write operation.

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 sentence, but it is under-specified rather than concise. It does not front-load critical information or earn its place with meaningful details. For 7 parameters and no annotations, the description should be more substantive.

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 complexity (7 parameters, no annotations, no output schema, no sibling differentiation), the description is completely inadequate. It fails to provide sufficient context for an agent to correctly select and invoke the tool, especially compared to siblings like 'record_decision'.

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 input schema has 0% description coverage, and the tool description provides no explanation of any parameters. Parameters like 'decision_id', 'session_id', 'learned', 'followups' are not described at all, leaving the agent without guidance on their semantics or usage.

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: 'Record the outcome of a previous decision or implementation.' It uses a specific verb ('Record') and identifies the resource ('outcome'). However, it does not differentiate from the sibling tool 'record_decision', which may also involve recording something related to decisions.

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. The description implies it is for recording outcomes after decisions or implementations, but there is no explicit when-to-use or when-not-to-use information, nor any mention of prerequisites or related tools.

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 bears full responsibility for behavioral disclosure. It only states the search action but omits details such as whether the search is across all sessions or limited to the current one, the order of results, or any side effects. This lack of transparency leaves the agent with significant unknowns.

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 redundant information. Every word serves a purpose, and it is appropriately sized for the tool's simplicity. This exceeds the requirements for conciseness.

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 simplicity, the description is too sparse. It lacks details about search scope, output format, and behavior with empty queries. For a search tool, more context (e.g., 'searches across all sessions' or 'returns matching decisions and reflections') would improve completeness.

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%, meaning the description does not elaborate on any parameters. It mentions 'query text' but does not explain that the 'query' parameter is the search string or that 'limit' controls result count. The description adds no value beyond the raw 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 'Search prior decisions and reflections by query text' clearly states the action (search), the resource (prior decisions and reflections), and the method (by query text). It differentiates from sibling tools like get_state (which retrieves current state) and record_decision (which creates data). However, it could be more precise about what 'state' encompasses.

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 no guidance on when to use this tool versus alternatives such as get_session or get_state. It does not mention exclusions or contexts where search_state is not appropriate. A user must infer usage from the name and siblings.

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 behavioral traits like side effects or permissions. It only states the core action (apply patch) without explaining outcomes (e.g., success/failure, idempotency, or whether the update is immediate). The schema clarifies array replacement, but the description adds minimal 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?

The description is a single, front-loaded sentence that efficiently communicates the tool's purpose without any extraneous words. Every part 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?

Despite good schema coverage, the description omits crucial details such as return value, error scenarios, and prerequisites (e.g., existence of state.json). Sibling tools like get_state imply state exists, but the description should clarify whether the update is transactional or the expected response.

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 input schema has 100% coverage and already describes the patch as a JSON merge patch with array replacement and the reason as a short string. The description adds 'record why' but does not enhance understanding beyond the schema, meeting the baseline for rich 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 clearly states the tool's action: applying a JSON merge patch and recording the reason. It specifies the resource (state.json) and the verb (apply), distinguishing it from read-only siblings like get_state or decision-related tools like record_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?

The description implies usage for updating state, but lacks explicit guidance on when to use this tool versus alternatives such as get_state or record_decision. No exclusion criteria or when-not-to-use advice is provided.

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