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

With no annotations, the description must disclose behavior but only states it returns audit logs. It omits whether the operation is read-only, destructive, or requires specific authentication or permissions. The ordering ('latest') is implied but not elaborated.

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 no extraneous information. Every word contributes to the purpose, achieving high conciseness.

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

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

Given no output schema and a simple parameter, the description is too minimal. It does not explain what an audit log entry contains, pagination, or error conditions. For a tool of this complexity, more detail is warranted to make it independently usable.

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 description mentions 'N' which corresponds to the 'limit' parameter, but does not explicitly map them or explain the parameter's effect beyond the implicit count. Schema coverage is 0%, so the description carries the burden but only minimally helps.

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 the latest N audit log entries. It uses a specific verb and resource, making the purpose unambiguous. However, it does not explicitly differentiate from sibling tools like zero_search or zero_read.

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

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

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

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

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

No annotations are provided, so the description carries the full burden. It discloses 'no validation', but fails to explain other behavioral traits like whether the capture is persistent, what happens to the data, or if there are side effects. Minimal transparency.

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

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

A single sentence that conveys the core purpose and key behavior. No redundant or unnecessary information. Front-loaded with the most important details.

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 capture tool with no output schema, the description should explain what happens after capture (e.g., return value, side effects). It only mentions the target and lack of validation, leaving significant gaps for an agent to understand the tool's full behavior.

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 already describes both parameters (text and domain) with 100% coverage. The description adds context about the target folder ('00_Fleeting'), but this does not add significant semantic meaning 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 states the verb 'capture' and the target '00_Fleeting', with traits 'lightest, no validation'. This clearly identifies the tool's purpose and distinguishes it from siblings like zero_write_note. However, it is in Thai, which may reduce clarity for non-Thai-speaking agents.

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

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

Implies use for quick capture without validation, but no explicit context about when to use this tool versus alternatives like zero_resolve or zero_write_note. The description does not provide when-not or alternative 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?

Description indicates it writes health.json and returns counts and top20, providing output structure. However, no annotations exist, and the description does not disclose side effects, permissions, or whether it is read-only, leaving some behavioral ambiguity.

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 a single sentence that efficiently conveys purpose and output. Could be slightly clearer for non-Thai speakers but overall earns its place.

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

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

Given no parameters, output schema, or annotations, the description covers main actions and return format. However, it omits details about dependencies (e.g., required files) and assumes default context, leaving some gaps.

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

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

No parameters exist, so schema coverage is 100%. Description adds value by detailing the scope of the health check, which is meaningful beyond the empty 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?

Description clearly states it performs a complete health check covering links.jsonl, frontmatter, body wikilinks, and packs, and outputs counts and top20. It distinguishes itself from siblings like zero_resolve and zero_write_note which handle different tasks.

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 or not use this tool versus alternatives, but its unique purpose among siblings makes usage implied. No exclusions or prerequisites mentioned.

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 exist, and the description fails to disclose whether the tool is read-only or modifies data, what side effects occur (e.g., overwriting Today.md), or any permissions needed.

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

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

The description is a single short sentence that conveys the core purpose and parameter behavior 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?

No output schema, and the description does not explain what the tool returns or how it interacts with other files (e.g., whether it creates or updates Today.md), leaving ambiguity.

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 0%, so the description compensates by explaining the only parameter (include_home) and its effect, though it lacks detail on exact behavior or default value.

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

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

The description clearly states it 'refreshes Today.md' with specific content (active + fleeting 24h), and distinguishes from siblings by focusing on a specific file and including a parameter to optionally include Home.md.

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 explains default behavior and how to include Home.md via include_home, but does not explicitly contrast with sibling tools or provide when-not-to-use 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 full burden. It states what is created but does not disclose side effects (e.g., overwriting existing files), required permissions, or whether the operation is destructive. This is a significant gap for an initialization action.

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 front-loaded with the action and listing key outputs. Every word contributes meaning without 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 adequately explains the tool's effect but could be more complete by specifying the scope (e.g., where the structure is created) and the outcome (e.g., returns success). It is minimally sufficient.

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 tool has zero parameters, and schema coverage is 100%. The description adds value by detailing what the tool creates, which is sufficient for a parameterless tool. Baseline 4 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 creates a Zero Brain folder structure with specific components (kernel files, skeleton packs, Home.md/Today.md), distinguishing it from sibling tools that handle different operations like resolving, capturing, or writing notes.

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 an initialization tool, likely used first in a workflow, but provides no explicit guidance on when to use it vs alternatives, prerequisites, or conditions under which it should not 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?

With no annotations, the description partially discloses behaviors: bidirectional linking, appending to a file, and deduplication. However, it omits error handling, authentication requirements, and whether existing notes are required.

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 in Thai that front-loads the primary action. While efficient, it could be better structured by separating the side effect.

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

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

Given 3 parameters, no output schema, and no annotations, the description covers the core function but lacks details on return value, prerequisites (e.g., note existence), and error scenarios. It is adequate but not thorough.

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 0%, so description must compensate. It explains from_id and to_id as note IDs but does not clarify the 'rel' parameter or ID formats. The side effect of appending to links.jsonl is mentioned but not tied to parameters.

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

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

The description clearly states the tool creates a bidirectional link between notes with an append-to-file side effect including deduplication. It is distinct from sibling tools like zero_resolve and zero_write_note.

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 usage guidelines are provided. The description does not indicate when to use this tool versus alternatives such as zero_resolve or zero_capture, nor does it specify prerequisites or caveats.

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 what it lists but does not disclose traits like read-only nature, potential side effects, or performance implications. For a read operation, this is minimal transparency.

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

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

The description is very short and to the point, but includes Thai text which may reduce clarity for non-Thai readers. Still, it efficiently states the purpose.

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 hints at the return value (packs with provenance) but does not specify output format, order, or limits. It is adequate for a simple list but could be more 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?

With zero parameters and 100% schema coverage, the description adds no parameter information, which is acceptable. Baseline 4 for 0 params 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 lists domain packs and their provenance status (verified/modified/unreviewed) relative to packs.lock.json. It uses a specific verb ('list') and resource ('domain packs + provenance'), distinguishing it from sibling tools that resolve, initialize, capture, etc.

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 zero_resolve or zero_init. The description does not mention prerequisites, contexts, or when not to use it.

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 mentions actions like regenerating Today.md and taking snapshots, but does not disclose whether these actions are destructive, require permissions, or have side effects (e.g., overwriting files, deleting queues). The 'cap 50' for fleeting queue implies a capacity constraint, but the behavioral impact is not fully explained.

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 line that front-loads the essential actions. It is concise, but could be slightly more structured (e.g., separating actions). Every component is listed, but no unnecessary text.

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 minimally adequate. It lists actions but lacks details on expected outcomes, failure modes, or side effects. For a tool with no parameters, this is borderline acceptable but leaves room for improvement.

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 tool has no parameters, so the description does not need to explain parameter details. It adds value by outlining the actions performed without needing schema compensation. A baseline of 4 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 lists the actions performed: fleeting queue (cap 50), regenerate Today.md, health, and snapshot to a specific path. While it is in Thai, the overall purpose as a nightly maintenance cycle is evident, and it is distinguishable from sibling tools like zero_resolve or zero_init.

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 other sibling tools. There is no mention of prerequisites, frequency, or conditions under which the nightly cycle should be triggered.

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. It discloses access control and audit behavior (T1/T2 tiers), but does not mention side effects or that it is a read-only operation. Partial behavioral disclosure.

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

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

The description is concise at one sentence, but the use of undefined abbreviations (T1, T2) and lack of up-front clarity on parameter reduce effectiveness. It is brief but could be more self-contained.

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

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

Given the complexity of access tiers and a single undocumented parameter, the description is incomplete. It does not explain output format, error states, or how the tier system works, leaving significant gaps for an agent.

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

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

The single parameter id_or_alias is not explained in the description and the schema provides no description (0% coverage). The agent has no guidance on what values are valid or the format expected.

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 reads notes including frontmatter and body, distinguishing it from sibling tools like zero_write_note and zero_search. However, the use of cryptic abbreviations T1 and T2 reduces clarity for those unfamiliar with the system.

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 conditions (T1 audit, T2 approval) but does not explicitly state when to use this tool versus alternatives or provide exclusions. Usage context is implied from the tool's purpose.

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 the matching priority (exact then fuzzy) but omits critical traits: whether it is read-only, what happens on no match, whether it returns multiple ids, or error behavior. This is insufficient for safe invocation.

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 (single sentence) and front-loads the core purpose. No wasted words, though it could benefit from structuring into usage and behavior sections for clarity.

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

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

With no output schema, no annotations, and a single parameter, the description should explain return value behavior (e.g., single vs. multiple ids, null on fail). It lacks this, leaving the agent uncertain about handling results.

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

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

Schema coverage is 0%, and the description adds minimal context: the single parameter 'name' is used for matching alias/title. It does not specify format, trimming, or case sensitivity. The description adds little beyond the schema field name.

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 id matching an alias or title, with exact then fuzzy matching. It implies a specific resource (alias/title) and action (resolve to id), which distinguishes it from sibling tools like 'zero_search' or 'zero_read'.

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

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

No guidance on when to use this tool versus alternatives. It describes the matching logic but does not specify prerequisites, when not to use, or alternative tools for other lookup scenarios.

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

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

With no annotations provided, the description fully bears the burden. It discloses search fields, the return of snippets, default exclusion of sensitive levels (T1/T2), the effect of include_private (returns T1+audit, T2 requires approval), and pagination via limit/offset. This is comprehensive for a read-only search 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 compendious sentence that conveys core functionality efficiently. It is front-loaded with the action and field list. However, the use of dashes and Thai characters may reduce readability for non-Thai agents, though it is still clear.

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 7 parameters, no output schema, and no annotations, the description covers the essential behavior (fields searched, snippet return, pagination, privacy flag) but lacks information on the meaning of T1/T2 beyond the described access rules, and does not specify the response structure or other parameters like 'tag' or 'domain'. It provides a minimum viable level of 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?

The input schema has 7 parameters but only 'limit' and 'offset' have descriptions (29% coverage). The description adds meaning for 'query' (searches title/aliases/tags/body) and 'include_private' (behavior regarding T1/T2), but it does not explain 'tag', 'type', or 'domain'. It partially compensates for low schema coverage but not fully.

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 explicitly states the tool searches across title, aliases, tags, and body, returning snippets. This clearly identifies the verb (search) and resource (items with those fields). The sibling tools (e.g., zero_resolve, zero_read) do not offer search, so this tool is well-differentiated.

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 some usage context, such as default exclusion of T1/T2 and behavior when include_private is set, but it does not explicitly advise when to use this tool over alternatives like zero_read for full content or zero_resolve for reference resolution. The guidance is implied but not comparative.

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 discloses key behavioral traits: partial update (only sent fields are modified) and immutability of id and created fields. This is sufficient for basic understanding, though it omits side effects, permissions, and return value.

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 short (one sentence) and front-loads the core idea, but it lacks necessary detail for an 8-parameter tool. It achieves conciseness at the cost of completeness.

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 8 parameters with no schema descriptions, the description should explain return behavior and parameter semantics. It does neither, and only weakly differentiates from zero_write_note via the partial update concept.

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

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

Schema description coverage is 0%, so description must compensate. It only mentions body and the constraint on id/created, but provides no explanation for other parameters like state, tags, add_links, etc. The meaning of 'add_links' and 'add_evidence' arrays is entirely unclear.

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 updates a note by editing only the sent fields, and explicitly prohibits editing id and created. This distinguishes it from create or full-write actions like zero_write_note.

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 implies partial update usage ('แก้เฉพาะฟิลด์ที่ส่ง') but does not explicitly mention when to use this vs alternatives, nor provide prerequisites or exclusions. The sibling zero_write_note suggests a create/full-write counterpart, but no direct comparison is made.

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

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

No annotations provided, so description must carry full burden. It reveals one behavioral rule (atomic/entity types require evidence ≥ 1) but omits critical traits like idempotency, whether updates are allowed, return behavior, or permissions. Transparency is insufficient.

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 a single sentence, making it concise but severely under-specified for a tool with 9 parameters. It is front-loaded with the main action but lacks structure. The brevity detracts from usefulness.

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 (9 parameters, no output schema, no annotations), the description is grossly incomplete. It omits parameter details, return format, prerequisites, side effects, and error handling, leaving the agent with insufficient context.

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

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

Schema description coverage is 0%, and the description only adds meaning for two parameters (type and evidence) by stating the evidence requirement. Other parameters (title, body, tags, links, domain, aliases, privacy) are left completely undocumented in both schema and description.

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

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

Description clearly states the tool writes a permanent note to a specific location (10_Notes) with a constraint for atomic/entity types. The verb 'write' and resource 'note' are specific, and the constraint distinguishes it from sibling tools like zero_update_note or zero_capture.

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. While the sibling list includes zero_update_note, the description does not indicate that this tool is for creation only or provide scenarios. Implied usage is weak.

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