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

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behaviors: it auto-bootstraps sessions if needed, handles fallbacks for parameters, deduplicates facts in mid-turn calls, and manages fact injection limits. However, it doesn't explicitly mention error handling or rate limits, leaving some gaps.

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 front-loaded with the core purpose but becomes lengthy with detailed call sequences and parameter notes. While all information is relevant, it could be more streamlined; some sentences, like those about host compatibility, add necessary detail but reduce 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 complexity (11 parameters, no annotations, no output schema), the description is largely complete. It covers purpose, usage, and key behaviors, but lacks details on return values or error handling, which would be helpful for an agent invoking this tool effectively.

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 11 parameters thoroughly. The description adds minimal parameter semantics beyond the schema, such as noting that 'message' is an alias for 'latestMessage' and explaining the purpose of 'pendingToolCall' and 'toolResult' in context. This meets the baseline for high schema coverage.

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: 'Ask Iranti whether memory should be injected before the next LLM turn.' It specifies the verb ('ask') and resource ('Iranti'), and distinguishes it from siblings by focusing on memory injection decisions rather than other memory operations like querying or writing.

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 explicit, detailed guidelines on when to use this tool: it lists a required call sequence with three specific scenarios (before replying, before lookup tools, after certain writes) and adds a rule for recalling facts. It also distinguishes usage from alternatives by specifying it's for memory injection decisions, unlike sibling tools for querying or writing.

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 carries the full burden of behavioral disclosure. It effectively explains that this tool persists data across turns, sessions, and agents, and that it writes to shared entities when entityTargets are supplied. It mentions what gets stored (e.g., current_step, next_step) but doesn't cover potential side effects like rate limits, authentication needs, or error handling.

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 well-structured and front-loaded, with the first sentence stating the core purpose. Each subsequent sentence adds meaningful context without redundancy. It efficiently covers usage scenarios, comparisons to alternatives, and behavioral implications in a compact form.

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 complex tool with 13 parameters and no output schema, the description does a good job explaining the tool's role and when to use it. However, it lacks details on return values or error conditions, which would be helpful given the tool's mutation nature and absence of annotations. The description compensates well but doesn't fully address all contextual gaps.

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 documents all parameters thoroughly. The description adds value by explaining the overall purpose of checkpointing and hinting at how parameters like entityTargets affect behavior ('writes canonical shared state... to those entities for handoff'), but doesn't provide additional syntax or format details beyond 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?

The description clearly states the tool's purpose: 'Persist a shared progress checkpoint while you work.' It specifies the verb ('persist') and resource ('shared progress checkpoint'), and distinguishes it from siblings by calling it 'the strongest shared-RAM tool for active work' and contrasting with 'ad-hoc prose.'

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 explicit guidance on when to use this tool: 'Use this at meaningful milestones' and 'prefer it over ad-hoc prose when you need another session or another agent to pick up where you left off.' It also mentions a specific alternative ('ad-hoc prose') and clarifies the tool's role relative to sibling tools by emphasizing its strength for active work handoff.

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 carries the full burden of behavioral disclosure. It effectively describes key behaviors: it returns 'operating rules plus prioritized relevant memory,' may include 'a backfill suggestion' for durable facts not in shared memory, and explains the postCompaction parameter's effect ('rules are only sent once per context window'). However, it doesn't mention error conditions, rate limits, 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 efficiently structured with zero wasted sentences. It front-loads the core purpose, provides clear usage guidelines, explains behavioral aspects, and distinguishes from alternatives—all in 7 concise sentences that each earn their 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?

For a tool with 6 parameters, no annotations, and no output schema, the description does an excellent job explaining purpose, usage, and key behaviors. It covers the tool's role in the workflow and distinguishes it from siblings. The main gap is the lack of output format details (what 'operating rules' and 'prioritized relevant memory' look like), which would be helpful given no output schema exists.

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 6 parameters thoroughly. The description adds some context about the postCompaction parameter ('Omit on normal mid-session handshake calls — rules are only sent once per context window'), but doesn't provide additional semantic meaning for other parameters beyond what the schema descriptions already state.

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: 'Initialize or refresh an agent's working-memory brief for the current task.' It specifies the verb (initialize/refresh), resource (working-memory brief), and distinguishes it from sibling iranti_attend by explicitly stating 'Do not use this as a per-turn retrieval tool; use iranti_attend.'

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 explicit guidance on when to use this tool: 'Call this at session start or when a new task begins' and 'If your host does not support a true session-start hook, call this on the first user turn before you start answering recall-style questions.' It also clearly states when NOT to use it: 'Do not use this as a per-turn retrieval tool; use iranti_attend.'

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 carries the full burden of behavioral disclosure. It does well by describing the return format ('ordered oldest-first'), listing the fields in each entry, and specifying a prerequisite action ('call iranti_attend before this'). However, it doesn't mention potential limitations like rate limits, authentication requirements, or error conditions, which would be helpful for a tool with no 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?

The description is well-structured and appropriately sized. It starts with the core purpose, then describes the return format, specifies a critical prerequisite, and ends with usage context. Every sentence adds value with no redundancy or wasted words. The information is front-loaded with the most important details first.

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 7 parameters, no annotations, and no output schema, the description does a good job covering purpose, usage guidelines, and return format. It provides the prerequisite information and context about what historical insights to expect. However, without annotations or output schema, it could benefit from more behavioral details like error handling or performance characteristics to be fully 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?

The schema description coverage is 100%, so the schema already documents all 7 parameters thoroughly. The description doesn't add any parameter-specific information beyond what's in the schema descriptions. It mentions 'entity+key pair' which aligns with the required parameters, but provides no additional syntax, format, or usage details for any parameters.

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 specific verbs ('Retrieve the full version history') and resources ('fact for an exact entity+key pair'). It distinguishes from siblings by specifying this is for historical data retrieval rather than current state queries or write operations, and explicitly mentions the sibling tool 'iranti_attend' as a prerequisite.

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 explicit usage guidelines: it states when to use ('to understand how a fact evolved over time'), when not to use (implies not for current state queries), and names a specific alternative/prerequisite ('call iranti_attend before this discovery tool'). It also gives context about what types of historical changes to examine ('decisions that changed, blockers that were resolved, values that were contested or superseded').

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 of behavioral disclosure. It mentions that the Librarian chunks text into atomic facts, which hints at processing behavior, but lacks critical details: it doesn't specify whether this is a read-only or mutating operation, what happens to the ingested data (e.g., storage, indexing), authentication needs, rate limits, or error handling. For a tool with no annotation coverage, this is a significant gap 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?

The description is a single, efficient sentence that directly states the tool's purpose without unnecessary words. It is front-loaded with the core action and outcome, making it easy to parse. Every part of the sentence contributes to understanding the tool's function, with zero 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 the complexity (6 parameters, no annotations, no output schema), the description is insufficiently complete. It lacks details on behavioral traits, output format (what 'atomic facts' look like), error conditions, and usage context relative to siblings. Without annotations or an output schema, the description should provide more context to guide the agent effectively, but it falls short.

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%, meaning all parameters are documented in the input schema. The description does not add any semantic details beyond what the schema provides (e.g., it doesn't explain the 'entity' format further or clarify the relationship between 'agent' and 'agentId'). According to the rules, with high schema coverage, the baseline score is 3, as the description doesn't compensate with extra parameter insights.

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 ('ingest a raw text block') and the outcome ('chunk it into atomic facts'), specifying both the verb and resource. It distinguishes this as an ingestion/chunking operation, which is different from siblings like query, search, or write tools. However, it doesn't explicitly contrast with specific siblings like 'iranti_write' or 'iranti_observe' to fully differentiate usage contexts.

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. With multiple sibling tools available (e.g., iranti_write, iranti_query, iranti_search), there is no indication of prerequisites, typical use cases, or exclusions. This leaves the agent without context for selecting this tool over others in the same server.

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 carries the full burden of behavioral disclosure. It mentions recovering facts 'that have fallen out of Claude context,' which implies retrieval from some external memory system, but doesn't describe authentication needs, rate limits, side effects, or what constitutes 'relevant facts.' This leaves significant gaps for a tool that appears to query a knowledge base.

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, efficient sentence that directly states the tool's purpose without unnecessary words. It's front-loaded and wastes no space, making it easy for an agent to parse quickly.

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 apparent complexity (retrieving facts based on context and hints) and lack of annotations or output schema, the description is minimally adequate but incomplete. It doesn't explain what 'facts' look like, how relevance is determined, or the tool's integration with Claude's context, leaving the agent with significant uncertainty about behavior and results.

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 parameters thoroughly. The description adds no additional parameter semantics beyond implying that 'currentContext' is used to identify lost facts, which is somewhat redundant with the schema. This meets the baseline for high schema coverage.

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: 'Recover relevant facts that have fallen out of Claude context.' This specifies the verb ('recover') and resource ('relevant facts'), though it doesn't explicitly differentiate from sibling tools like 'iranti_history' or 'iranti_search' that might also retrieve information.

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. It doesn't mention prerequisites, context for usage, or compare it to sibling tools like 'iranti_query' or 'iranti_search', leaving the agent to infer usage scenarios.

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 carries the full burden of behavioral disclosure. It effectively describes the tool's behavior: it's a retrieval operation that returns specific data fields (value, summary, confidence, etc.), requires a prerequisite call to 'iranti_attend', and has a specific protocol tracking mechanism via agent parameters. The only minor gap is lack of explicit mention about whether this is a read-only operation or has side effects.

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 well-structured and appropriately sized. It uses clear paragraphs to separate different aspects (purpose, prerequisites, usage guidelines, comparison). While efficient, it could be slightly more concise by combining some related concepts into fewer sentences.

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 no annotations and no output schema, the description does an excellent job providing context. It explains what the tool does, when to use it, prerequisites, and what it returns. The only minor gap is that without an output schema, more detail about the return structure would be helpful, though the listed fields (value, summary, confidence, etc.) provide reasonable guidance.

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 parameters. The description doesn't add significant parameter semantics beyond what's in the schema - it mentions 'entity+key' but doesn't provide additional context about format, constraints, or usage of the agent parameters. This meets the baseline expectation when schema coverage is complete.

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 specific verbs ('retrieve', 'lookup') and resources ('current fact', 'entity+key'). It explicitly distinguishes this tool from its sibling 'iranti_search' by stating 'prefer this over iranti_search when the target fact is already known', providing clear differentiation.

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 explicit usage guidelines: it states when to use ('when you already know both the entity and the key'), when not to use ('do not answer from memory alone before checking Iranti'), prerequisites ('call iranti_attend before this discovery tool'), and alternatives ('prefer this over iranti_search'). This gives comprehensive guidance for proper tool 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. While 'Create' implies a write/mutation operation, the description doesn't address permissions needed, whether the operation is idempotent, what happens on conflicts, rate limits, or what the response looks like (since there's no output schema). This leaves significant gaps for an agent to understand how to use it safely and effectively.

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, clear sentence with no wasted words. It's front-loaded with the core action and resource, making it easy to parse quickly.

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 5 parameters, no annotations, and no output schema, the description is insufficient. It doesn't explain what happens after creation (e.g., success/failure responses), error conditions, or how it fits with sibling tools. The agent would need to guess about behavioral aspects and usage 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 100%, meaning all parameters are documented in the schema itself. The description doesn't add any additional semantic context about the parameters beyond what's in the schema (e.g., it doesn't explain relationship types or entity formats in more detail). This meets the baseline for high schema coverage.

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 ('Create') and resource ('relationship edge between two entities'), making the purpose immediately understandable. However, it doesn't differentiate this tool from sibling tools like 'iranti_related' or 'iranti_related_deep', which might also handle relationships in some way.

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. With sibling tools like 'iranti_related' and 'iranti_related_deep' that might handle relationship queries, there's no indication of when creation is appropriate versus retrieval, or any prerequisites for using this 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?

No annotations are provided, so the description carries the full burden. It discloses that this is a 'discovery tool' for graph traversal and mentions memory injection dependencies, but lacks details on permissions, rate limits, or error handling. It adds some context but not comprehensive behavioral traits.

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 front-loaded with the main purpose and follows with a critical requirement. Both sentences earn their place, but the structure could be slightly improved by separating the prerequisite into its own line for clarity.

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 annotations and no output schema, the description provides adequate context for a discovery tool with dependencies. However, it lacks details on return values, error cases, or performance characteristics, leaving some gaps in completeness for a tool with graph traversal functionality.

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 parameters. The description does not add any meaning beyond what the schema provides for parameters like 'entity', 'agent', or 'agentId'. Baseline 3 is appropriate when 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?

The description clearly states the verb ('Read directly related entities') and resource ('entities for a given entity'), specifying the scope ('1 hop'). It distinguishes from sibling tools like 'iranti_related_deep' by focusing on immediate relationships only.

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 explicitly states when to use this tool: 'REQUIRED: call iranti_attend before this discovery tool.' It provides a clear prerequisite and distinguishes it from other discovery tools by specifying its role in the workflow.

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 that this is a 'discovery tool' for 'graph traversal' and has a prerequisite call, which adds behavioral context. However, it doesn't mention permissions, rate limits, or what 'Read' entails (e.g., read-only vs. side effects), leaving gaps 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?

The description is two sentences with zero waste. The first sentence states the purpose, and the second provides critical usage guidance. It's appropriately sized and front-loaded with essential 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?

Given no annotations and no output schema, the description is incomplete. It explains the purpose and prerequisite but lacks details on behavior (e.g., what 'Read' returns, error handling) and doesn't compensate for the missing structured data. However, it's adequate for a basic 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 100%, so the schema already documents all parameters. The description adds no parameter-specific information beyond implying 'N hops deep' relates to the 'depth' parameter. This meets the baseline of 3 when schema coverage is high.

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: 'Read related entities up to N hops deep for a given entity.' This specifies the verb ('Read'), resource ('related entities'), and scope ('up to N hops deep'). However, it doesn't explicitly differentiate from sibling tools like 'iranti_related' or 'iranti_relate', which likely have overlapping functionality.

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 explicit usage guidance: 'REQUIRED: call iranti_attend before this discovery tool so Iranti can decide whether memory should be injected before graph traversal.' This clearly states a prerequisite and when to use this tool (after 'iranti_attend'), though it doesn't mention alternatives 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 are provided, so the description carries the full burden. It discloses that the tool uses a 'narrow summary extractor' similar to a 'Claude Stop hook' and is 'explicit and works for Codex or any MCP client,' adding context about its operational scope and compatibility. However, it lacks details on error handling, persistence mechanisms, or side effects.

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 appropriately sized and front-loaded, with every sentence adding value: the first states the purpose, the second provides usage examples, and the third adds behavioral context and exclusions. There is no wasted text, and it's structured for clarity.

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 (a tool for persisting summaries with 7 parameters) and no annotations or output schema, the description is reasonably complete. It covers purpose, usage guidelines, and some behavioral context, though it could benefit from more details on what 'strict durable summary' entails or how summaries are stored. The lack of output schema means return values aren't explained, but the description compensates adequately.

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 7 parameters thoroughly. The description adds no specific parameter semantics beyond implying that 'response' should contain the assistant's text with summary patterns. With high schema coverage, the baseline score of 3 is appropriate as the description doesn't enhance parameter understanding significantly.

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: to persist a strict durable summary from the assistant's own response using a specific extractor. It specifies the verb ('persist') and resource ('strict durable summary'), though it doesn't explicitly differentiate from sibling tools like 'iranti_checkpoint' or 'iranti_write' which might have overlapping functionality.

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 explicit usage guidelines: use after specific phrases like 'the next step is...', 'the blocker is...', etc., and not for arbitrary prose or every turn. It distinguishes when to use this tool versus alternatives by specifying the narrow scope of application.

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 carries the full burden of behavioral disclosure. It effectively describes the tool's behavior: it's a search tool for discovery when exact keys are unknown, uses hybrid search, and requires calling iranti_attend first. However, it doesn't mention potential limitations like rate limits, error conditions, or what happens if no results are found, which would be helpful for an agent.

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 well-structured and concise, with four sentences that each serve a distinct purpose: stating the tool's function, specifying its use case, providing a prerequisite, and giving a concrete example of when to use it. There is no wasted text, and key information is front-loaded.

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 (9 parameters, no annotations, no output schema), the description does a good job of explaining the tool's purpose, usage, and prerequisites. However, it doesn't describe the return format or what results look like, which would be important for an agent to interpret outputs. The lack of output schema means the description should ideally cover this, but it provides enough context for basic usage.

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 9 parameters thoroughly. The description adds no specific parameter semantics beyond implying that 'query' should be natural language. Since the schema does the heavy lifting, the baseline score of 3 is appropriate, as the description doesn't significantly enhance parameter understanding beyond what's in 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?

The description clearly states the tool's purpose: 'Search shared memory with natural language when the exact entity or key is unknown. Uses hybrid lexical and vector search across stored facts.' It specifies the verb ('search'), resource ('shared memory'), and method ('hybrid lexical and vector search'), distinguishing it from exact lookup tools like iranti_query.

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 explicit usage guidelines: 'Use this for discovery and recall, not exact lookup' and 'If the user asks what they previously told you and you do not know the exact key, use this before saying you do not know.' It also specifies a prerequisite: 'REQUIRED: call iranti_attend before this discovery tool so Iranti can decide whether memory should be injected before search,' clearly differentiating when to use this tool versus alternatives.

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 of behavioral disclosure. It mentions this is a 'discovery tool' for 'provenance discovery,' implying it's a read-only operation to retrieve information about agents and facts. However, it lacks details on permissions, rate limits, response format, or potential side effects. The description adds some context but is incomplete for a tool with no 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?

The description is appropriately sized and front-loaded: the first sentence states the purpose, and the second provides critical usage guidelines. Every sentence earns its place with no wasted words, making it efficient and easy 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?

Given no annotations, no output schema, and 3 parameters with full schema coverage, the description is partially complete. It covers purpose and usage prerequisites well but lacks behavioral details (e.g., response format, error handling) and does not explain return values. For a discovery tool with no structured output information, more context would be helpful, but it meets a minimum viable level.

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 parameters ('entity', 'agent', 'agentId') with descriptions. The description does not add any parameter-specific semantics beyond what the schema provides, such as explaining the 'entity' format in more detail or clarifying the relationship between 'agent' and 'agentId'. Baseline is 3 when 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?

The description clearly states the tool's purpose: 'List which agents have written facts about an entity.' This is a specific verb ('List') + resource ('agents') + scope ('have written facts about an entity'). However, it does not explicitly differentiate from sibling tools like 'iranti_history' or 'iranti_query', which might also involve listing or querying information.

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 explicit usage guidelines: 'REQUIRED: call iranti_attend before this discovery tool so Iranti can decide whether memory should be injected before provenance discovery.' This specifies a prerequisite (call 'iranti_attend' first) and context for when to use this tool, with a clear alternative or preparatory step named.

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 carries the full burden of behavioral disclosure. It effectively describes key behaviors: the tool writes durable facts (mutation), requires immediate calls (timing constraint), handles conflicts automatically ('Conflicts on the same entity+key are detected automatically and may be resolved or escalated'), and mentions personal-memory key handling. However, it doesn't cover error handling, rate limits, or authentication requirements, leaving some gaps 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 well-structured and front-loaded with the core purpose. Most sentences earn their place by providing critical guidance (timing, examples, conflict handling). However, it could be slightly more concise—some phrasing is repetitive (e.g., multiple 'before the next action' examples), and the paragraph format might benefit from bullet points for the timing examples.

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 (mutation tool with 11 parameters, no annotations, no output schema), the description does a good job of covering essential context: purpose, timing, conflict handling, and parameter semantics. It adequately compensates for the lack of annotations and output schema by explaining behavioral traits and usage. However, it doesn't describe the return value or error responses, which would be helpful for a write operation.

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 baseline is 3. The description adds meaningful context beyond the schema: it explains that 'confidence is optional and defaults to 85', clarifies the purpose of 'propertiesJson' ('when you need structured issue or workflow metadata such as issueStatus=open|resolved, severity, or resolution notes'), and mentions 'Personal-memory keys honor the configured canonical personal entity.' This provides valuable semantic guidance for several parameters, elevating the score above baseline.

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: 'Write one durable fact to shared memory for a specific entity.' It specifies the verb ('write'), resource ('durable fact'), and destination ('shared memory'), distinguishing it from siblings like iranti_query (read) or iranti_ingest (bulk). The description explicitly contrasts with batching/deferring, further clarifying its singular write operation.

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 explicit, detailed guidance on when to use this tool: 'Call IMMEDIATELY when a fact is confirmed — do not batch or defer to end of turn.' It gives concrete examples (after editing a file, running a command, getting search results) and states the purpose ('when you learned something concrete that future turns, agents, or sessions should retain'). It also mentions alternatives implicitly by contrasting with batching/deferring, though it doesn't name specific sibling tools as alternatives.

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 carries the full burden of behavioral disclosure. It explains key behavioral traits: the tool writes issue facts, preserves history by archiving prior states when status changes, and uses stable keys (issueId always maps to issue_<id>). However, it doesn't mention permissions, rate limits, or error handling, leaving some gaps 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 appropriately sized and front-loaded. The first sentence states the core purpose, followed by usage guidelines and behavioral context. Every sentence adds value without redundancy, making it efficient and well-structured.

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 complexity (16 parameters, write operation) and no annotations or output schema, the description does a good job covering purpose, usage, and key behaviors. However, it lacks details on return values, error cases, or authentication needs, which would be helpful for a write tool with many parameters.

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 16 parameters thoroughly. The description adds minimal parameter semantics beyond the schema, only mentioning 'issueId' and 'status' in context. It doesn't provide additional syntax, format details, or usage examples for parameters.

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: 'Write a canonical open or resolved issue fact on a stable key.' It specifies the verb ('write'), resource ('issue fact'), and scope ('canonical'), and distinguishes it from sibling tools by explicitly contrasting with 'iranti_write' for hand-rolling issueStatus properties.

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 explicit usage guidance: 'Use this when you want defects, bugs, or chores to remain first-class shared memory instead of loose prose' and 'Prefer this over hand-rolling issueStatus properties through iranti_write when the fact is specifically a trackable issue lifecycle entry.' It clearly states when to use this tool versus an alternative (iranti_write).

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 carries the full burden of behavioral disclosure. It effectively describes key behavioral traits: that rules persist across sessions, are stored as entities, and surface conditionally during iranti_attend. However, it doesn't mention potential side effects, error conditions, or what happens if a rule with an existing ruleId is written, leaving some behavioral aspects 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?

The description is perfectly structured and concise with zero wasted words. It front-loads the core purpose, explains the mechanism, provides a concrete example, and concludes with persistence information—all in three efficient sentences that each earn their 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?

For a creation/mutation tool with 8 parameters, no annotations, and no output schema, the description provides good contextual completeness. It explains the tool's purpose, when to use it, how rules function, and their persistence. However, it doesn't describe what happens on success/failure or return values, which would be helpful given the absence of output schema and annotations.

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 100% schema description coverage, the schema already documents all 8 parameters thoroughly. The description adds minimal parameter semantics beyond the schema, only implying that 'rule' contains guideline text and 'triggers' match against attend context. This meets the baseline of 3 since the schema does the heavy lifting, but the description doesn't significantly enhance parameter understanding.

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 specific verbs ('write a task-scoped user operating rule') and resources ('rule/<rule_id> entities'), and distinguishes it from siblings by explaining its unique function of creating rules that surface during iranti_attend based on trigger keywords. It provides concrete examples like 'always use GitHub Releases, not npm publish' triggered by specific keywords.

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 explicitly states when to use this tool ('for recurring guidelines that should be applied to specific task types') and provides a clear alternative context by mentioning that rules 'surface during iranti_attend only when the current context matches one or more trigger keywords.' This creates a direct relationship with the sibling tool iranti_attend, giving clear usage context.

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