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

No annotations are provided, so the description carries the behavioral disclosure burden. It does add a meaningful constraint that facts must be verified, but it does not disclose duplicate handling, mutability, update/delete behavior, or what the response looks like after a successful add.

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 sentence, front-loaded with the verb and resource, and no filler. The em-dash efficiently defines the key concept of verification without adding unnecessary length.

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 low-complexity additive tool with fully documented required parameters and no nested objects, the description plus schema is largely sufficient for an agent to select and invoke it. The only notable gaps are return semantics and duplicate-update behavior, which are not essential for a basic 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 100%, and the source parameter has useful examples ('resume', 'client confirmed', 'linkedin'). The description reinforces the verification concept but adds little meaning for content or category beyond what the schema already states, so the baseline 3 applies.

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

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

The description names a clear action ('Add'), a specific resource ('a single verified career entry'), and defines what qualifies as verified ('confirmed from a document or directly by the client'). This differentiates it from the bulk ingestion siblings like atlas_ingest_resume and atlas_ingest_linkedin, as well as from other add_* tools.

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?

It explicitly states when to use this tool: for a single fact that has been verified from a document or directly by the client. This implies not for unverified or bulk data, though it does not explicitly name alternative tools or give a when-not-to-use list.

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. 'Track a new goal' only loosely implies creation and does not state that this creates a persistent goal record, whether it is idempotent, what side effects occur, or what the response looks like. For a mutation tool with no annotation safety signals, this is a significant gap.

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, compact sentence with no filler. It front-loads the core action and resource before mentioning optional additions. It earns a high score for brevity, though slightly more detail could have been added without harming 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?

With 5 parameters, 3 required fields, an enum, no annotations, and no output schema, the description is too sparse. It does not clarify what 'track' means operationally, whether the goal is immediately persisted, or what success looks like. An agent would need to infer important behavioral details from the tool name and schema alone.

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 modest value by identifying milestones and target_date as optional, which helps an agent understand required vs. optional inputs, but it does not explain nuances like the lens enum or ISO date format beyond what the schema already provides.

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 uses a clear action ('Track') with a specific resource ('a new goal') and mentions the optional fields. It distinguishes the create operation from the sibling atlas_update_goal by emphasizing 'new,' though it does not explicitly name the sibling. The scope is evident enough for an agent to understand this tool creates a goal.

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 this is for creating a new goal rather than updating an existing one, but it provides no explicit guidance on when to choose this tool over siblings like atlas_update_goal or atlas_track_commitment. It does not state prerequisites, exclusions, or scenarios where an alternative should be used.

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 only states that a pattern is recorded; it does not mention whether the record is appended to a profile, whether it is reversible, what side effects occur, or what the tool returns. This is a significant gap 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?

Two short sentences with no filler. The action and scope are front-loaded, and the Therapist-lens context is stated efficiently.

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

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

The tool is simple and its parameters are fully documented in the schema, but there is no output schema and no annotation coverage. The description does not explain what happens after recording or how the recorded pattern is used beyond 'build psychological context.' This is adequate but minimal.

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 every parameter. The description adds minimal semantic value beyond naming pattern types, which are already enumerated in the schema. Baseline 3 is appropriate.

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

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

The description uses a specific verb ('Record') with a specific resource ('pattern') and names the pattern categories (behavioral, emotional, cognitive). It also ties the tool to the Therapist lens, which helps distinguish it from sibling tools like atlas_add_career_fact and atlas_add_goal.

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 clear context: this tool is for capturing psychological patterns for the Therapist lens. It does not explicitly state when not to use it or name alternatives, but the contextual cue is strong enough to guide tool selection among the 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 carries the behavioral burden. It does disclose that the tool 'Returns a framework' and describes the approach as 'structured multi-lens,' which is helpful. However, it does not state whether the analysis is persisted, whether it is read-only, or any side-effect expectations.

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, focused sentence that front-loads the core behavior and then states the return value. Every word earns its place; there is no filler or redundancy.

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 and no annotations, the description should clarify more about what the returned framework contains and whether the analysis is stored. It gives enough to attempt a call, but leaves meaningful ambiguity about the output structure and side effects.

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's mention of career, business, and life changes aligns with the type enum but adds no detail about how 'context' affects the analysis or how the parameters interact.

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 identifies the tool's action ('analysis') and resource ('opportunity'), and it specifies the domains it applies to (career moves, business decisions, life changes). It does not explicitly contrast with siblings, but the purpose is distinct enough from nearby ingest/search tools.

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?

It gives concrete usage context: use this when evaluating a career move, business decision, or life change. It does not state exclusions or point to an alternative tool like atlas_search_advice_history, so it stops short of full routing guidance.

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 explaining behavior beyond the action. It does not disclose whether completion is reversible, what state changes occur, how the commitment is affected, or any permissions 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 a single clear sentence with no filler. It front-loads the action and object and remains appropriately sized for the simple operation it describes.

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 two-parameter operation, the description plus schema provides enough to make a basic call. However, with no annotations and no output schema, it lacks disclosure of side effects, completion semantics, and expected response behavior, leaving a noticeable gap.

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

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

Schema description coverage is 100%, and the schema already documents commitment_id and notes adequately. The description adds no additional parameter-level meaning beyond reinforcing the completion action, so the baseline score of 3 is appropriate.

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

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

The description states a concrete action ('Mark') on a specific resource ('a commitment') with a clear outcome ('completed'). It is easily distinguishable from siblings like atlas_track_commitment, which implies tracking rather than finalizing a commitment.

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 gives no guidance on when to use this tool versus alternatives such as atlas_track_commitment or atlas_update_goal. It also does not mention prerequisites, conditions, or whether it should be used only after certain criteria are met.

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

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

With no annotations, the description carries the burden, and 'Retrieve' clearly indicates a read-only operation while 'full client profile across all advisory lenses' defines the data scope. It does not mention response formatting, freshness, or authorization, but these are secondary for a zero-parameter 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?

The description is a single sentence, front-loaded with the verb 'Retrieve', followed by a compact em-dash list of data categories. Every phrase contributes useful scope information and there is no redundancy or 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 zero-parameter reader with no output schema, the description names the main return categories and the 'full...all advisory lenses' qualifier, which gives an agent enough to know what outcome to expect. It could be more explicit about which client profile is being read, but the sibling set and no-parameter schema make that context largely inferable.

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 zero parameters and annotation coverage is 100%, so there are no parameter semantics for the description to add. The baseline score of 4 applies because no parameter documentation is 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 uses a specific verb ('Retrieve') and a specific resource ('full client profile'), and enumerates the lenses it spans — career facts, patterns, goals, accountability, functional data. This makes it clearly identifiable as a holistic read tool and distinguishable from sibling mutation/ingestion tools like atlas_update_profile or atlas_add_career_fact.

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 wording implies a holistic read-only use case via 'full client profile across all advisory lenses', but it does not explicitly state when to use this tool versus single-lens alternatives or search history. No when-to-use or when-not-to-use guidance is provided beyond what the name and scope imply.

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 carry the full burden of explaining side effects. It only says 'Analyze...' and never discloses whether the tool persists the raw text, writes observed patterns to a profile, or merely returns analysis. The name includes 'ingest', suggesting persistence, but the description does not confirm or explain that behavior.

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

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

The description is a single sentence with no filler and a clear front-loaded verb and object. It is concise, though the missing usage and side-effect context means the brevity comes at some cost.

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?

This is an ingestion-oriented tool with no annotations and no output schema, yet the description does not clarify what happens after analysis, whether data is stored, or whether observed_patterns is intended as an input or a result. These are material gaps for an agent deciding whether and how to invoke it.

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 source, raw_text, and observed_patterns are already documented in the JSON Schema. The description adds only the general theme of pattern analysis and contributes no additional meaning to individual 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 states a concrete action ('Analyze') on a specific resource ('past conversation transcripts') and names the analytic outcomes ('behavioral patterns, recurring themes, psychological insights'). It doesn't explicitly differentiate this from sibling ingest tools or atlas_add_pattern, but the chat-history resource is distinct enough to orient an agent.

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 phrase 'past conversation transcripts' implies the tool is meant for conversational text, but there is no explicit when-to-use guidance, no named alternatives, and no exclusions. The agent must infer fit from the resource type rather than from stated selection criteria.

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 behavioral disclosure burden. It clearly marks this as a write operation ('Store') and adds a scoping behavior ('Focus on SNPs relevant...'), but it does not explain how existing SNP data is handled, whether irrelevant SNPs are ignored or rejected, or what happens after ingestion.

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 no wasted words. The first sentence states the core action and data source; the second adds domain scope. Every sentence earns its place and the most important 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 there is no output schema and no annotations, an agent would still be uncertain about operational expectations: whether ingestion appends or replaces data, whether out-of-scope SNPs are silently dropped, and what the response contains. The schema fully covers inputs, but the description leaves these behavioral gaps unaddressed.

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% description coverage, with detailed explanation of `source` and `snps`, including an example of the nested structure and field requirements. The description itself adds no parameter-level details, but the schema is sufficient, so the baseline score of 3 applies.

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

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

The description clearly states the verb 'Store' and the resource 'SNP/genetic data from services like 23andMe or Ancestry', making the tool's purpose explicit. It also names the relevant domain (performance, stress response, sleep, cognition) and is clearly distinct from sibling tools like atlas_ingest_resume or atlas_ingest_health_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?

The description provides useful context on when to use the tool: when storing genetic data from consumer DNA services, and it narrows scope to SNPs relevant to performance, stress response, sleep, and cognition. It does not explicitly name alternatives or negative cases, but the sibling ingest tools are different enough that this scoping gives an agent sufficient direction.

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

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

With no annotations, the description carries the full burden of behavioral disclosure. 'Store' signals a write operation, but the description does not say whether data is appended, overwritten, merged, validated, or deduplicated, nor what happens to existing records. This is insufficient for a mutation/injection 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 a single, front-loaded sentence that communicates the core purpose efficiently with useful examples. There is no filler, redundant phrasing, or restatement of the tool name.

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 write tool with no annotations and no output schema, the description should clarify storage semantics, data shape expectations, and behavior with existing records. It only identifies the domain and leaves important operational context uncovered, which is incomplete for reliable 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 100%, so parameter meaning is already well documented by the schema itself. The description adds category examples that roughly map to the 'category' enum, but it does not add meaning beyond the schema's property descriptions. Baseline 3 is appropriate.

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

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

The description states a specific action ('Store') and resource ('health-related information'), with concrete examples (lab results, sleep data, nutrition logs) that make the tool's domain clear. It is distinguishable from resume, LinkedIn, and chat history ingest tools, though the broad phrase 'other health-related information' could blur the boundary with atlas_ingest_genetic_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?

There is no guidance about when to choose this tool over alternative ingest tools. No exclusions, conditions, or sibling references are provided, so an agent must infer usage solely from the tool name and general category. This is a clear gap given the large sibling set.

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

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

With no annotations, the description carries the full burden of behavioral disclosure. It only says 'Store', revealing a write operation but nothing about overwrite/append semantics, idempotency, whether raw_text is parsed, or what happens to existing profile data. This is a meaningful gap for an ingest 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 a single front-loaded sentence with no filler. It earns its place by naming the resource and purpose, though it is too sparse to fully carry behavioral and usage guidance.

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 underspecified for an ingest/write tool. It does not explain expected side effects, data flow, return behavior, or how this relates to existing profile data. The schema covers parameters well, but contextual behavior is largely missing.

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

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

Schema description coverage is 100%, and both parameters (raw_text and extracted_facts) already have meaningful descriptions in the schema. The tool description adds no parameter-specific detail, so the baseline of 3 applies.

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

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

The description states a specific action ('Store') and resource ('LinkedIn profile data'), and connects it to a clear purpose ('career context building'). It is distinguishable from sibling ingest tools by naming LinkedIn as the data source, though it could more explicitly contrast with atlas_ingest_resume.

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 when to use the tool: when the agent has LinkedIn profile data that should be stored for career context. However, it does not explicitly state when not to use it, nor does it name alternatives like atlas_ingest_resume or atlas_update_profile.

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 implies a mutation ('store') and mentions a required pre-processing step, but it does not disclose side effects, duplicate handling, idempotency, authorization needs, or failure behavior. For a write operation, this is a significant gap.

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

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

Two concise sentences with no filler. The primary purpose is front-loaded, and the prerequisite is clearly stated in the second sentence. 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?

The tool is simple in terms of parameters and schema coverage, but there is no output schema and no annotations. The description covers the core operation and prerequisite but omits return value, error conditions, and storage semantics, leaving the agent under-informed for a state-changing 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 100%, so the schema already fully documents both raw_text and extracted_facts. The description adds no new parameter-level meaning beyond referencing 'structured facts', which aligns with the schema's extracted_facts property.

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

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

The description states a specific verb and resource: 'Parse and store career facts extracted from resume text.' It is clearly resume-specific and distinguishable from sibling ingest tools such as atlas_ingest_linkedin, though it 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?

The description gives an explicit prerequisite: 'Claude should extract structured facts before calling this.' This tells the agent what must happen before invocation, which is useful. However, it does not mention when not to use the tool or how it compares to similar tools like atlas_add_career_fact.

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 disclosure burden. 'Log an advisory session for continuity' clearly indicates a persistent write action, and the usage timing adds useful behavioral context. However, it does not mention side effects, whether the log can be retrieved later, or any safety implications beyond the act of logging.

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

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

Two short sentences with no filler. The core action is front-loaded, and the usage trigger is stated immediately after. Every word 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?

For a simple logging tool with four fully documented required parameters and no output schema, the description provides the essential purpose and trigger. It could mention that logged sessions are preserved for later reference, but the phrase 'for continuity' implies this sufficiently.

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 each parameter already has a clear definition. The description adds no additional parameter-level detail, which is acceptable given the schema already documents all four required fields.

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

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

The description states a specific verb ('Log'), a clear resource ('advisory session'), and the purpose ('for continuity'). It also distinguishes this from sibling tools by framing it as a session-logging action rather than an ingest, profile, or goal 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 gives explicit timing guidance: 'Call this at the end of meaningful conversations.' It does not name alternative tools or exclusion conditions, but the context is clear enough for an agent to decide when this tool applies.

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 states the action ('Create a new client profile') but does not disclose how duplicates are handled, whether the tool is idempotent, what side effects occur, or what the response contains. This leaves important behavioral unknowns 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 two sentences with no filler. The primary action is front-loaded, and the onboarding context adds useful direction without wasting words.

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

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

The description correctly identifies purpose and onboarding position, and the schema covers all parameters. However, there is no output schema and no mention of what the tool returns (e.g., client ID), which is important for orchestrating subsequent onboarding steps. Moderate gaps keep it at 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 fully documents each parameter (name, email, summary, background, goals_overview). The tool description does not add further parameter meaning, but it does not need to; the baseline of 3 applies.

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

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

The description states a specific verb and resource: 'Create a new client profile for ATLAS advisory.' It clearly distinguishes this tool from profile updates, reads, and data ingestion siblings. The context 'first step in the onboarding process' further clarifies its role.

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 clear context: it is the first step in onboarding, implying it should be called before other profile-related tools like atlas_update_profile or atlas_get_profile. It does not explicitly contrast with alternatives or state when not to use it, so it stops short of a 5.

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 does disclose the core behavior — shows all commitments and flags overdue ones — and 'review' implies a non-mutating action. However, it does not explicitly state read-only/no side effects, auth requirements, or what the returned data looks like, which matters more given there is no output schema.

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 sentence with the main clause front-loaded and zero fluff. The overdue-detection clause earns its place as the key differentiator, and no structured fields or annotations need to be duplicated.

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

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

For a zero-argument review tool this is nearly sufficient: the agent knows what it shows and that no input is needed. But with no annotations and no output schema, the description leaves gaps around return structure, side-effect profile, and explicit routing between this and atlas_track_commitment.

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?

Zero parameters means there is nothing for the description to explain beyond the empty schema; baseline 4 applies. The phrase 'all commitments' usefully reinforces that no filtering scope exists.

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 uses a specific verb ('review') and resource ('commitments') with a clear scope ('all') and a distinguishing feature ('automatic overdue detection'). It reads as a read-side overview tool and is visually distinct from the ingest/add/update siblings, though it does not name a specific sibling to disambiguate from.

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 word 'Full' implies the comprehensive overview use case, and the sibling set hints at alternatives (e.g. atlas_track_commitment for individual tracking), but no explicit when-to-use or when-not-to-use guidance is provided. An agent must infer routing from the name and one-liner.

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. 'Search' and 'check' imply a read-only operation, but the description does not explicitly state that nothing is modified or describe what the returned matches look like. This is adequate for a simple lookup but not deeply transparent.

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

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

Two short, purposeful sentences. The operation is stated first, and the practical usage rule follows immediately. There is no filler or redundancy.

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

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

The tool is simple: one required parameter, no output schema, no nested objects. The description provides both the operation and the trigger condition for use. It could mention what the search returns, but the core information needed to invoke it correctly is present.

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

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

Schema description coverage is 100%, and the query parameter already has a clear description ('Search term or topic to look for in past advice'). The tool description adds no additional parameter semantics, so the baseline score of 3 is appropriate.

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

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

The description clearly states the verb ('Search'), the resource ('past advice'), and the purpose ('ensure consistency'). It stands apart from the sibling tools, which are all ingest/add/update/log operations, making this the unambiguous retrieval tool.

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

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

The description gives explicit guidance on when to use the tool: 'Always check before giving advice on topics you've covered before.' It does not mention exclusions or alternative tools, but since no sibling offers similar search functionality, the usage 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 are provided, so the description carries the full burden of behavioral disclosure. 'Log' implies a write operation, but it does not mention whether duplicate commitments are allowed, whether it updates existing records, what permissions are needed, or what the response contains. For a mutation tool with zero annotation coverage, this is a significant gap.

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-structured sentence with no wasted words. It front-loads the action and resource, then adds the deadline and purpose efficiently.

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 tool with only three parameters and no output schema, the description covers the essential purpose and context. It does not explain return values or lifecycle interactions with sibling tools, but those are not strictly necessary for a basic logging action.

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 all three parameters are already documented in the schema. The description adds minimal value beyond reinforcing that a deadline is part of the commitment, so the baseline of 3 is appropriate.

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

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

The description clearly states the action 'Log' and the resource 'commitment', with the deadline being a key component and accountability tracking as the purpose. It is specific enough to understand the core function, though it does not explicitly differentiate from sibling tools like atlas_complete_commitment.

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 gives clear context: use this when a client has made a commitment that needs a deadline for accountability tracking. It does not explicitly mention alternative tools or when not to use it, but the context is sufficient for most cases.

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, but it only restates the operations. It does not explain side effects of changing status, whether milestone completion is irreversible, permissions needed, or interaction between status and milestone parameters.

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

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

A single, front-loaded sentence with no filler, earning its place. It is somewhat lean given the tool mutates multiple aspects, but it is not overgrown.

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

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

For a mutation tool with no annotations and no output schema, the description is too thin. It omits how the operations interact, what happens after completion, and any constraints beyond the schema.

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

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

Schema description coverage is 100%, so the schema already documents all parameters. The description adds no new semantic detail beyond what the schema provides, so baseline 3 is appropriate.

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

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

The description names the resource (goal) and specific operations (update status or complete milestones), which is clear and distinct from atlas_add_goal. It does not explicitly distinguish from siblings like atlas_complete_commitment, but the scope is evident from the verb and noun.

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 given on when to use this tool versus alternatives such as atlas_add_goal or atlas_track_commitment. The verb 'update' weakly implies an existing goal, but there are no explicit conditions, 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 are provided, so the description carries the full burden. It discloses that this updates specific sections, but it does not explain partial-update behavior, whether unspecified fields remain unchanged, whether an existing profile is required, or any side effects. This is minimal behavioral disclosure 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 a single, front-loaded sentence with no filler words. It is concise and to the point, though the brevity sacrifices some useful detail.

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

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

For a mutation tool with no annotations, no output schema, and five optional parameters, the description is too thin. It does not state that at least one field should presumably be provided, how the target client is identified, or what happens when only some fields are supplied, leaving important invocation details ambiguous.

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%, with every parameter already documented ('Updated name', 'Updated email', etc.). The description adds only the framing of 'sections' but no extra meaning about how the parameters behave, which is adequate given 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 has a clear verb ('Update') and resource ('the client profile'), and states that it modifies specific sections rather than the whole profile. This distinguishes it as a mutation tool from read/ingest siblings like atlas_get_profile and atlas_ingest_resume, though it 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?

The description gives no guidance on when to use this tool versus siblings such as atlas_onboard_client or atlas_update_goal. It only implies use by the word 'Update'; no exclusions, prerequisites, or alternative-selection cues are provided.

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