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

With no annotations, the description must disclose behavioral traits. It mentions 'VSA transform' (suggesting vector operations) and 'returns the best completions,' but does not state whether the tool is read-only, requires specific permissions, or has side effects. The absence of any disclosure about destructive behavior or resource usage leaves the agent uncertain.

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—a single sentence with no superfluous words. However, it could be slightly restructured to first state the verb and then the pattern; still, no wasted 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?

Despite having an output schema (not shown), the description lacks essential context for a 6-parameter tool. It does not explain the analogy task's prerequisites, the role of notes_dir and glob, or the nature of 'best completions.' The agent would need additional information to use the tool effectively.

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

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

The input schema has 0% parameter description coverage, so the description must fill the gap. It only references a, b, c in the analogy pattern but does not define them, nor does it explain notes_dir, glob, or k. The agent is left to infer that a, b, c are strings and that k controls the number of results, but this is not explicit.

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 purpose: solving analogies in the form a:b::c:? using a VSA transform on notes. It mentions returning the best completions, which distinguishes it from sibling tools like codebook_neighbors (finding neighbors) or codebook_query (general queries). However, it could be more explicit about the output format or that it returns multiple candidates.

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 codebook_related or codebook_walk. The description does not specify prerequisites, limitations, or typical use cases. An agent would not know if this tool is for semantic analogies or simple string matching, or when to prefer it over other retrieval methods.

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. Description says 'Index' which could imply mutating the directory, but doesn't clarify if the index is persistent or temporary, or if any side effects occur. Lacks info on auth, rate limits, or destructive potential.

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, zero waste. First sentence states purpose and output; second gives usage guidance and parameter hints. Perfectly front-loaded and efficient.

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

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

Given low parameter count and no output schema, the description covers the tool's core behavior and return value. Could benefit from noting that this tool is a prerequisite for other codebook tools, but the sibling names provide indirect 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?

With 0% schema coverage, the description adds meaning: notes_dir is described as 'a local path' and glob 'picks files'. This clarifies the parameters beyond their titles, though more detail (e.g., supported glob patterns) could improve understanding.

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

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

The description clearly states the tool indexes a local notes folder and returns codebook contents (id + title per note). This distinguishes it from siblings like codebook_analogy or codebook_query, which operate on already indexed 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?

Explicitly says 'Run this first to see what's in a directory', providing clear when-to-use context. Does not explicitly state when not to use or name alternatives, but the sibling tool names imply this is the initial setup 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?

The description reveals one behavioral detail: 'pure cosine similarity'. However, with no annotations, it does not disclose whether the tool is read-only, required permissions, side effects, or performance implications. This is a partial disclosure that leaves gaps.

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

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

The description is a single, concise sentence that gets to the point quickly. It could be improved by adding structure (e.g., listing key parameters), but it is not 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?

Despite having an output schema, the description fails to explain parameter semantics, usage context, or behavioral traits beyond the similarity metric. The presence of four parameters with no commentary makes the description incomplete for effective tool use.

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 provides no explanation for any of the four parameters (notes_dir, note_id, glob, k). With 0% schema coverage, this is a critical omission; the agent cannot understand how to set parameters beyond their names and types.

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 finds nearest notes to a given note using cosine similarity, which is specific and indicates a retrieval operation. However, it does not explicitly differentiate from siblings like codebook_related or codebook_query, which might have similar 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?

No guidance is provided on when to use this tool versus alternatives (e.g., codebook_related, codebook_query). There is no mention of prerequisites, scenarios, or exclusions, leaving the agent without decision support.

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 bears full burden. It mentions 'geometrically' but does not explain what that entails (e.g., vector embeddings, similarity measure). It also omits whether the tool is read-only, requires network access, or has side effects.

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

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

The description is a concise single sentence (14 words) that front-loads the action and resource. Every word contributes meaning with zero 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 the tool has 4 parameters, an output schema, and no annotations, the description is too minimal. It fails to explain the geometric method, the meaning of 'most related', or how the parameters affect behavior. Important context 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_description_coverage is 0%, yet the description provides no information about any parameters (notes_dir, text, glob, k). The agent receives no help understanding parameter roles or expected inputs 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 finds notes related to a phrase using geometric similarity, explicitly contrasting with keyword and LLM-based methods. This specificity distinguishes it from typical 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?

The description implies usage for semantic search but provides no guidance on when to use this tool over siblings like codebook_neighbors or codebook_related. No exclusions or alternatives are 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?

The description explains the algorithm (geometric neighbors + algebraic link-recall) but does not disclose side effects, permissions, rate limits, or the nature of the combination (e.g., union or intersection). With no annotations, the description bears full responsibility.

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, concise but at the expense of completeness. It front-loads the core purpose but omits necessary 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?

The tool has four parameters and an output schema, but the description does not explain parameter semantics, output format, or usage context. It is insufficient for an agent to use the tool 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?

The description adds no meaning beyond parameter names like 'notes_dir' and 'note_id'. Parameters 'glob' and 'k' are not explained, and schema coverage is 0%. The description fails to clarify the role of any parameter.

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 tool finds related notes using combined geometric neighbors and algebraic link-recall. It implies retrieval but lacks an explicit verb like 'retrieve' or 'find'. It distinguishes from sibling tools like codebook_neighbors by mentioning the combined method.

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 codebook_neighbors or codebook_query. There are no usage conditions 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 full burden. It discloses the core behavior (repeated prediction via LINKS) but does not mention whether the operation is destructive, what happens on missing start_id, or how the walk terminates beyond the step count default.

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

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

The description is a single, front-loaded sentence that efficiently states the tool's purpose, though a brief expansion on parameters would not harm conciseness.

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

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

Given the output schema exists, the description does not need to explain return values, but it lacks information on parameters and the nature of the LINKS relation, making it insufficient for an agent to confidently invoke the 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?

With 0% schema description coverage, the description should compensate, but it only explains the overall action. It does not clarify the meaning of notes_dir, start_id, glob, or steps, leaving the agent to infer from parameter names 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 performs a 'reasoning walk' that starts from a note and repeatedly predicts the next note via the LINKS relation, which distinguishes it from siblings like codebook_neighbors (likely single-step) or codebook_query.

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

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

The description provides no guidance on when to use this tool versus alternatives or when not to use it. No exclusions or context for sibling differentiation beyond the implication of repeated traversal.

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