Persistent Project Context for xAI Grok

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

No annotations are provided, so the description should disclose behavioral traits. However, it only states a determination without mentioning side effects, idempotency, or whether external calls are made. This is insufficient for a mutation-unaware 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 a single, concise sentence with no wasted words. It could be improved by adding key details without becoming verbose.

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

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

Given the tool's simplicity (one parameter, no output schema), the description is minimally complete. However, it lacks explanation of the output, the meaning of 'FULL/DELTA/X-DELTA', and what 'soul' refers to, leaving gaps for new users.

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 description adds no additional meaning beyond what the schema already provides for the 'topic' parameter. 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 uses a specific verb ('determine') and identifies the resource ('topic' and 'soul' types). It clearly states what the tool does, but does not explicitly differentiate from siblings, which include other analysis 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?

No guidance is provided on when to use this tool versus alternatives, such as faf_gate or faf_score. There is no discussion of prerequisites, exclusions, or typical use 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 provided, the description carries the full burden. It discloses 'Two WASM calls, sub-millisecond total,' giving performance insight, but does not mention read-only nature, error behavior, or prerequisites. Adequate but could be more comprehensive.

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. The first immediately states the outputs, and the second adds technical detail. No wasted words, front-loaded with key 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 a single simple parameter, no output schema, and no annotations, the description is reasonably complete. It covers what the tool returns and performance. Minor lack of output format details, but acceptable.

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

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

Schema coverage is 100%, with the parameter 'content' described as 'Raw .faf YAML content to analyze.' The description adds no additional meaning beyond the schema, so 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 tool's function: 'One-call composite — returns score, tier-ready, valid, and engine identifier.' It uses a specific verb-resource combination and distinguishes from sibling tools that handle individual tasks like faf_score, faf_validate, and faf_get_tier.

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

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

The description implies usage as a composite alternative to individual sibling tools by stating 'One-call composite.' However, it does not explicitly state when not to use it or provide direct alternatives, which would strengthen 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?

The description discloses caching details (KV-cached with 1h TTL), edge deployment, and being environment-aware. Lacking annotations, it does not explicitly state read-only nature or potential side effects, but the search purpose is non-destructive.

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 three sentences covering purpose, behavior, requirements, and context. While dense, it avoids verbosity and front-loads key information, though it could be slightly more streamlined.

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

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

Given no output schema, the description explains return structure. With no annotations, it covers prerequisites and caching behavior. It also references related tools (faf_section) for hybrid retrieval, providing sufficient context for 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?

With 100% schema coverage, the description adds no additional detail to parameters beyond what the schema provides. It mentions output format but not parameter semantics, so it meets the baseline without exceeding it.

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 'semantic search over a Grok Collection' with specific outputs ('matched chunks (content, score, file)') and distinguishes from sibling faf_section by mentioning it is for structural search and that this tool composes with it for hybrid retrieval.

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 requires the XAI_API_KEY secret and suggests composition with faf_section for hybrid retrieval, providing clear context on prerequisites and complementary usage. However, it does not explicitly state when not to use 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 full burden falls on the description. It discloses key behavioral traits: sub-millisecond performance, zero allocations, and use of the Zig WASM engine. This adds useful information beyond basic purpose.

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, front-loaded with purpose followed by performance details. Every word adds value with no 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?

For a simple tool with one parameter, the description covers purpose, technical details, and usage context. No output schema is needed as the return value (token count) is implied.

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 only parameter 'content' is fully described in the schema ('Content to estimate tokens for.'). The description adds no additional semantic meaning, so baseline 3 is appropriate given 100% 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 estimates token count for arbitrary content, using a specific engine. The verb 'estimate' and resource 'token count' are explicit, and the name distinguishes it from sibling tools which perform analysis, search, or other functions.

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 mentions it is 'useful for context-budget planning', which gives clear context for when to use. However, it does not specify when not to use or provide alternative tools.

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

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

With no annotations, the description carries full burden. It discloses the core behavior: scoring, token estimation, deterministic verdict based on thresholds (defaults 85/8000). It also adds nuance about edge parity and hold-hint slots. Lacks details on error handling or side effects, but sufficient for a gate 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 three sentences, front-loaded with purpose, each sentence providing unique value. No redundancy, efficient word choice, and well-structured for quick comprehension.

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

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

Given no output schema, the description mentions the verdict but doesn't specify the exact output format. However, for a deterministic gate tool, it covers the essential logic and constraints. Minor gap in output specification.

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

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

Schema coverage is 100% with parameter descriptions. The description adds extra meaning by explaining the promotion condition (score >= min_score AND tokens <= max_tokens) and default values, which aids understanding beyond the schema alone.

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 is a Phase III pre-promotion quality gate that scores .faf content, estimates tokens, and returns a deterministic promote/hold verdict. It distinguishes itself from siblings like faf_score and faf_analyze by focusing on the gate decision before promotion to a Grok Collection.

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 indicates when to use (before promotion to Grok Collection) and implies the context (Phase III FRC). It does not explicitly state when not to use or name alternatives, but the context is clear enough for an AI agent to infer usage boundaries.

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 full burden. It discloses the return type and input range but does not mention that it is a read-only lookup with no side effects or performance characteristics. Adequate but missing explicit behavioral context.

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

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

Two sentences with no wasted words. The first sentence immediately states the action and output. 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?

For a simple one-parameter lookup with no output schema, the description covers input and output sufficiently. It provides example tier symbols and mentions the canonical tier-table, which adds helpful context. Slightly vague on whether returns are case-sensitive or exact format, but overall 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?

Schema description coverage is 100%, so the parameter is already documented. The description adds no new meaning beyond what the schema provides (repeat of 'numeric score'). 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 'Resolve' and clearly states the resource 'FAF tier' and the input 'numeric score'. It names the output 'tier symbol' with examples, distinguishing it from siblings like faf_score (which likely returns raw score) and faf_gate.

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

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

No guidance on when to use this tool versus alternatives like faf_score or faf_analyze. The description implies its purpose but does not state exclusions or context for choosing 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 full burden. It discloses that the tool is read-only (selects facts), preserves provenance, and never grades. It does not mention side effects, auth needs, or rate limits, but the query-only nature is clear.

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 sentences efficiently convey purpose, filtering dimensions, and a key behavioral constraint (no scoring). No wasted words; front-loaded with 'query'.

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

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

Given no output schema, the description lacks information about return format or structure. While it covers purpose and filtering, an agent might benefit from knowing the output shape (e.g., list of facts with provenance). Adequate but not 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?

Schema coverage is 100% (all parameters described in schema). The description adds value by explaining behavior when filters are omitted and clarifying that 'query' does case-insensitive substring matching. This goes beyond the schema definitions.

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 queries the durable .fafm model by type, tag, priority, and text, and explicitly distinguishes it from scoring tools. This differentiates it from siblings like faf_score.

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 mentions 'Phase III (FRC)' for context and advises that omitting filters gives a structured summary. It clarifies that the tool selects facts, not grades them, but does not explicitly name alternative tools for scoring.

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

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

No annotations provided, so description carries full burden. It explicitly discloses deterministic execution, two execution modes with different capabilities (WASM-pure vs filesystem access), and that it is advisory-only (never auto-fires). This is thorough and honest.

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

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

Description is well-structured with clear sections: main purpose, input details, execution modes. It is information-dense but not overly verbose. Could be slightly more concise, but front-loading key info is effective.

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 and no output schema, description fully covers inputs, behavior, execution environment, and return value structure (Recommendation with fields and hints). No gaps remain for an agent to invoke correctly.

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

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

Schema coverage is 100%, baseline 3. Description adds value by explaining each parameter's role and what analysis it enables (e.g., 'Enables drift detection' for fafm). This goes beyond the schema's simple descriptions.

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

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

Description clearly states it takes raw content strings and runs deterministic drift + contradiction signals to return a structured Recommendation. Distinguishes from siblings like faf_analyze (which likely just analyzes) and faf_gate (which gates) by specifying it orchestrates multiple inputs into a recommendation.

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?

Description explains execution modes (light-lane vs heavy-lane) and that it is advisory-only, providing context for when to use. Does not explicitly mention when not to use or alternatives, but the context is clear enough for an agent to decide.

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

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

Discloses return range (0-100 capped), performance (sub-ms), and engine parity with other tools. Lacks mention of side effects or permissions, but as a scoring tool, it's likely read-only.

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

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

Three sentences, each adding distinct value: engine, output range, parity, performance. No wasted words, front-loaded with the main action.

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?

Adequately explains return values and performance for a simple scoring tool. Lacks error handling details but is sufficient given no output schema and a single parameter.

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 covers 100% of parameters, and the description adds extra detail (auto-extraction for souls with [faf] section). This provides meaningful context 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 scores .faf YAML content using a specific engine (Mk4 Zig-WASM) and returns a capped score (0-100). It differentiates from siblings by focusing on scoring rather than validation or analysis.

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

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

No explicit guidance on when to use this tool over siblings like faf_analyze or faf_validate. The description implies scoring but does not specify contexts 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?

Without annotations, the description carries the burden. It discloses that the tool returns exact, whole sections with structure preserved, and contrasts with blind chunking. It could mention error handling or limits, but overall good.

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 that packs key information: phase, purpose, examples, and alternative usage. It is front-loaded and efficient, though a minor reorganization could improve scannability.

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

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

Given the tool's simplicity (2 params, no output schema), the description covers core functionality and usage. It could mention return format, but for the complexity level it is adequate.

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

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

Schema coverage is 100%, but the description adds value by explaining the dotted path format with examples and the behavior when section is omitted (list all paths). This goes beyond the schema's simple descriptions.

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

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

The description clearly states the tool returns an exact, whole .faf section by dotted path, with examples like 'stack' and 'human_context'. It also distinguishes from siblings by calling it the 'deterministic complement to blind chunking' and noting it can list all paths.

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 indicates when to use it (Phase III FRC, deterministic) and provides a usage hint ('Omit section to list every path'). However, it lacks explicit when-not-to-use or alternatives among the many sibling tools.

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

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

No annotations are provided, so the description must disclose behavioral traits. It reveals the validation logic (returns true if >= 100) and implies a read-only operation, but does not mention error handling, side effects, or requires permissions. This is minimally adequate given the tool's simplicity.

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

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

The description is extremely concise with two sentences, no redundant information, and clearly front-loads the core purpose. Every word contributes meaning.

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 simple single-parameter input and no output schema, the description is fairly complete. It explains the validation condition and return value, though it could optionally mention error cases or performance characteristics. The presence of many siblings slightly reduces completeness since usage guidance is 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 coverage is 100% for the single 'content' parameter, with a clear description in the schema. The tool description adds no extra semantic value beyond the schema, meeting the baseline but not exceeding it.

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 specifies the action (validate), the resource (.faf YAML content), and the success condition (returns true if mission-ready with score >= 100). This distinguishes it from sibling tools by mentioning the Mk4 Zig-WASM engine and the threshold.

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

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

No explicit guidance on when to use this tool versus alternatives. With 18 sibling tools, the description lacks context for selecting this tool, such as prerequisites, limitations, or comparisons to faf_analyze or faf_score.

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

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

No annotations provided, so description bears full burden. It discloses extraction of README and package.json, but does not mention side effects, authentication, rate limits, or failure modes. Somewhat transparent but gaps remain.

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

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

Description is concise (two sentences) and front-loaded with key action. However, it could benefit from structure like bullet points for extracted outputs. Slightly dense but efficient.

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

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

For a single-parameter tool, description covers input (public GitHub repo), process (extract, analyze), and output (.faf content, quality score, metadata). No output schema, so description sufficiently explains returns. Missing error scenarios but acceptable.

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

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

Schema coverage is 100% with a clear description of 'repo' parameter. Description adds no new semantic information about the parameter; it repeats the same format. 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?

Description clearly states the tool generates a .faf file from a GitHub repo without cloning, and specifies it extracts 6 Ws and analyzes stack. This differentiates it from sibling tools like faf_analyze or faf_validate.

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?

Only implies usage by mentioning 'from any public GitHub repository without cloning' but does not explicitly state when to use vs. alternatives or provide exclusions. No guidance on repository prerequisites or limitations.

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

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

No annotations provided, so description carries full burden. It only states 'Returns structured AI context' without disclosing side effects, error handling, or permissions.

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

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

Single sentence, concise and front-loaded. Could be slightly more informative but 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?

Adequate for a simple 1-param tool with no output schema, but does not explain return structure or behavior. Sibling tools suggest more detail needed.

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

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

Schema coverage is 100%, so baseline 3. Description adds no extra meaning beyond the schema's parameter description.

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

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

Description uses specific verb 'fetch' and resource 'context soul by name', clearly stating the action and outcome. It distinguishes from sibling 'list_souls' by specifying fetch by name.

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

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

No guidance on when to use this tool vs alternatives like list_souls or search_context. The description lacks context for selection.

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

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

No annotations are present, so the description carries full burden. It only states the purpose, with no disclosure of read-only nature, permission requirements, rate limits, or return characteristics. This is insufficient for a tool with no structural metadata.

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

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

Single sentence, front-loaded, no waste. 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 parameterless tool, the description is adequate but not complete. It could mention whether the output is paginated or requires authentication, but given the lack of output schema and annotations, it meets a minimum viable standard.

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 zero parameters. Baseline is 4 per guidelines. The description does not add parameter details (none needed), but it also does not miss anything.

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

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

Description clearly states the tool lists all available context souls. It is specific with verb 'List' and resource 'available context souls'. While not explicitly distinguishing from siblings, the sibling list includes 'get_soul' and 'search_context', so the scope is inferred.

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

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

No guidance is provided on when to use this tool versus alternatives like 'get_soul' or 'search_context'. The description lacks context for decision-making, such as prerequisites or limitations.

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

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

No annotations provided, so description carries full burden. It correctly indicates a read-only listing operation with counts, but lacks details on error handling, permissions required, or whether the tool is paginated.

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 with no wasted words. It is front-loaded and immediately understandable.

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 low complexity (1 param, no output schema), the description adequately explains what the tool does, but omits details about output format, potential errors, or limits. It is minimally 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?

Schema description coverage is 100% for the single parameter 'soul', with a basic description 'Soul identifier'. The tool description adds no further semantic value, so 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 'list', the resource 'unique tags', the scope 'in a soul', and the additional output 'with counts'. It distinguishes from siblings like 'search_by_tag' which likely performs a different 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?

No guidance on when to use this tool versus alternatives like 'search_by_tag' or 'tag_intel'. The description does not mention when not to use it or any prerequisites.

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

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

With no annotations, the description carries full burden. It discloses the scoring mechanism (Mk4 Zig-WASM Enterprise scorer, 33-slot), the process flow (drift → refresh → re-grounded), and optional drift reporting. This provides useful behavioral context beyond a simple 're-ground' statement.

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

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

Three sentences front-load the purpose and key details. The last sentence ('Built for Grok, by request.') is slightly extraneous but not harmful. Overall concise 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?

The description covers main behavior (re-grounding, scoring, drift, stamp) but lacks details on output format beyond 'stamped re-ground' and does not address error conditions or input validation. Given no output schema, more explicit return value explanation would improve completeness.

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

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

Schema coverage is 100% with good descriptions for each parameter. The tool description does not add significant new semantics for the parameters beyond what the schema already provides. 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 clearly states the tool re-grounds .faf content, re-scores via a specific scorer, reports drift, and returns a stamped re-ground. It distinguishes itself as 'the explicit re-grounding primitive for long sessions', differentiating from sibling tools like faf_score which likely just score without re-grounding.

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

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

The description implies usage for long sessions and mentions 'drift → refresh → re-grounded', but does not explicitly state when to use this tool over alternatives like faf_score or delta_check. No exclusions or when-not-to-use guidance is provided.

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

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

No annotations are provided, so the description carries full burden. It does not disclose behavioral traits such as read-only nature, error handling, performance characteristics, or what happens when no entries match. For a search tool, minimum transparency would include noting it is a read operation and response format.

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 very concise (one sentence) but lacks necessary detail. It is appropriately front-loaded but under-specified, missing critical context for an agent to use the tool effectively.

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

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

Given no output schema and no annotations, the description is incomplete. It does not explain what 'entries' are, whether results are filtered, paginated, or ordered, or how to interpret the output. This is insufficient for an agent unfamiliar with the domain.

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

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

Schema coverage is 100%, so baseline is 3. The description does not add meaning beyond the schema: it restates that it searches by tag and soul. No additional semantics or formats are provided.

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 finds entries in a soul by a specific tag. It uses a specific verb and resource, and the purpose is distinguishable from sibling tools like list_tags (which lists tags) and search_context (which searches context). However, it does not explicitly differentiate from tools like faf_analyze.

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

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

No guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites, exclusions, or specific contexts, leaving the agent to infer usage from the name and schema alone.

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

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

Mentions token-efficient return of matching lines, but no annotations exist; lacks disclosure on safety, rate limits, 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?

Single sentence, front-loaded, and to the point with no 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?

With no output schema, description explains return format; sufficient for a simple search with few 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 covers both parameters with descriptions (100% coverage), so description adds minimal value beyond that.

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?

Clearly states full-text search across souls, and differentiates from siblings by specifying it returns only matching lines for token efficiency.

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?

Implied usage for full-text search, but no explicit guidance on when to use versus siblings like search_by_tag or faf_collections_search.

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

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

No annotations are provided, so the description must disclose behavioral traits. It mentions 'discover' and 'suggest', implying read-only behavior, but does not explicitly state mutability, authentication needs, rate limits, or what gets destroyed. Adequate but not comprehensive.

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 sentences, no redundancy, front-loaded with the main purpose. 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?

The description covers the core functionality well, including the optional parameter. However, it does not describe the return format or output details, which would be helpful given no output schema. Still, for a simple tool with one optional param, it is largely 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?

Schema coverage is 100%, so the description's addition is minimal. It paraphrases the parameter's purpose ('Optional: suggest tags for this specific handle') without adding new meaning beyond 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 specific verbs ('discover', 'suggest') and resources ('tag patterns', 'co-occurrence', 'candidates', 'merge suggestions', 'namepoints'), clearly defining the tool's scope. It distinguishes from siblings like list_tags and search_by_tag by focusing on analysis and suggestions.

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

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

The description implies usage for analyzing tags, but does not explicitly state when to use this tool versus alternatives or provide exclusion criteria. No guidance on prerequisites or when not to use.

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