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

Discloses key behaviors: validates limits, returns one-time use confirm_token, operator must pass token, Claude cannot generate it. With no annotations, the description carries the burden and does well, though it could mention failure modes or token 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?

Two sentences plus a list. Every sentence adds value: purpose, token behavior, and action-parameter mapping. No fluff, front-loaded.

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

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

Covers purpose, token lifecycle, action mapping, and operator role. Missing minor details like error handling, but for a validation step, it is sufficiently complete to guide 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?

Despite 0% schema description coverage, the description fully documents each action's expected params (e.g., jog {dx,dy}, set_paper_origin {x,y}). This compensates completely for the schema's lack of detail.

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 this is Step 1 of any movement, validates limits, and returns a unique confirm_token. It lists the actions (jog, set_paper_origin, etc.) that can be used, distinguishing it from sibling execution tools like jog or production_run.

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 it is the first step before any movement, that the operator passes the token to the execution tool, and that Claude must not generate or guess the token. It lists the valid actions and their expected params, providing clear when-to-use and alternatives.

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

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

With no annotations, the description carries the full burden. It states 'records' but does not disclose whether this overwrites existing records, requires prior measurements, or has any side effects. The behavioral impact of the tool is unclear.

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

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

The description is a single sentence, concise and to the point. It front-loads the main purpose but could be better structured with a list or more explicit formatting. No extraneous 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 7 parameters, no output schema, and a calibration workflow context, the description is too sparse. It does not explain the workflow (e.g., measure then record), the role of this tool among siblings, nor the expected outcome. The description leaves 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 description adds meaning for 4 of 7 parameters (descent, clean speed, width, spring) but the schema has zero descriptions. It does not explain 'pen', 'paper', or 'notes'. Although some parameters are elaborated, the coverage is incomplete, and the description only partially compensates for the missing schema 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 states it records a measured record for pen and paper, listing some parameters. It conveys that the tool saves calibration data, but it does not clearly distinguish from similar tools like 'test_plot' or 'set_pen_positions'. The verb 'Grava' indicates saving, but the scope and purpose could be more explicit.

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. Among many calibration-related siblings, there is no mention of prerequisites or conditions that make this tool appropriate.

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 bears full responsibility for behavioral disclosure. It states the tool 'recompiles' with measured calibration, but does not clarify side effects (e.g., whether it modifies original data, requires specific calibration state, or has destructive potential). The mechanism of calibration application is unexplained.

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 without extraneous text. It is front-loaded and efficient, but its conciseness comes at the cost of omitted details about parameters and behavior.

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 (3 required params, no output schema, no annotations), the description is far too sparse. It does not explain what 'CALIBRATED' means, how the toolpath is modified, or what the output format is. The user would need external knowledge to effectively use 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?

The input schema has three required parameters (pen, paper, signature_id) with zero description coverage. The tool description provides no explanation of these parameters, their purpose, format, or constraints. The parameter semantics are entirely dependent on the schema titles, which are minimal.

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 'Recompila o toolpath com a calibração MEDIDA', clearly indicating the tool recompiles a toolpath with measured calibration. It references related tools (test_plot, lock) and the output state 'CALIBRATED', distinguishing it from a non-calibrated compile. However, it could be more explicit about the differentiation from sibling compile_toolpath.

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 via 'é o que test_plot/lock usam', suggesting that this tool is used when building calibrated toolpaths for those operations. It provides context but lacks explicit when-to-use, when-not-to-use, or alternative tools (e.g., compile_toolpath). The guidance is inferred, not direct.

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 mentions 'NOMINAL' and 'pre-calibration' but discloses no behavioral traits such as side effects, required permissions, or output format. The agent cannot infer safety or effects from this alone.

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 it is slightly under-specified. It includes pen options inline but lacks structure like separate sections. It is not verbose, but could better front-load essential 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?

Given the tool's simplicity (two params, no output schema), the description is incomplete. It omits explanation of the essential 'signature_id' parameter and any prerequisites or workflow context, such as the proof stage. More context is needed for effective 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?

Schema coverage is 0%, so description must add meaning. It only lists possible pen values but does not explain the role of 'signature_id' or how 'pen' affects compilation. No additional semantics beyond the schema 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 compiles the NOMINAL toolpath for pre-calibration proof, specifying the verb 'compile' and resource 'toolpath NOMINAL'. It implicitly distinguishes from the sibling 'compile_calibrated' by noting pre-calibration, providing specific purpose and scope.

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 does not provide explicit guidance on when to use this tool versus alternatives like compile_calibrated. It only implies usage for proof and pre-calibration, but lacks clear when-not or context-based recommendations.

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 discloses that mock doesn't move, but missing details on side effects (e.g., disconnection of previous connection), error behavior, or required states. 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?

Very concise (two fragments), front-loading the verb and resource. Could be slightly more structured but no wasted words.

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

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

Adequate for a simple tool with one parameter and no output schema. Covers basic behavior, but lacks return value info and error handling. Enough to use but could be improved.

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 'kind' is fully explained, listing the two allowed values and their meanings. Since schema has 0% description coverage, this adds value 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 connects to a plotter and distinguishes two connection kinds (nextdraw and mock). This verb+resource structure is specific enough, though it does not explicitly differentiate from sibling 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 on when to use this tool vs. alternatives. With many sibling tools for motion and calibration, the description lacks context on prerequisites or typical 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?

No annotations are provided, and the description does not disclose behavior such as side effects, required permissions, or error handling. The mention of 'confirm_token' suggests a confirmation step, but no details are given.

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 but fails to be concise; it is ambiguous and lacks structure. It mixes English and Spanish unnecessarily, reducing 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, one parameter barely described, and unclear behavioral context, the description is insufficient for an agent to use the tool correctly or safely.

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% description coverage, and the tool description adds no meaning to the 'confirm_token' parameter beyond its name. The description does not clarify what the token is or how to obtain 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 says 'Homing' but does not explain what homing entails. It references 'arm_motion' but the relationship is unclear, and it fails to distinguish from the sibling tool 'arm_motion'.

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 'arm_motion' or other siblings. The description provides no context for appropriate 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?

No annotations provided, so burden falls on description. It only mentions returning status and signature_id, but not side effects, permissions required, or behavior on failure. The name implies a write operation (import), but description suggests read-only validation, which is unclear.

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

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

The description is a single sentence, concise and to the point. However, it could be slightly more structured with separate lines for input and output.

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

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

For a tool with one parameter, no output schema, and no annotations, the description leaves too much unspecified: what is Profile v1, what is a centerline, what does 'validates' entail, and what are the possible status values. Incomplete for reliable agentic 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?

Parameter 'svg_path' has no description in schema (coverage 0%) and the tool description does not elaborate on its format (e.g., file path, URL, content). No added 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 validation of SVG centerline against Profile v1, but the tool name 'import_signature_svg' suggests import rather than validation. This mismatch reduces clarity. The description does not specify what 'import' means or how validation relates to import.

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. The description does not mention prerequisites, expected input format, or related tools. Sibling tools exist but no hints are given.

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 that a confirm_token is required and that arm_motion must be called first. However, it does not describe side effects, error states, or whether the operation is safe/reversible, leaving gaps in transparency.

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

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

The description is extremely concise with no filler words. The '[MOVE]' tag provides quick categorization. Every sentence is essential, making it easy to parse.

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

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

Given the lack of annotations and output schema, the description is incomplete for a physical movement tool. It omits details on coordinate system, error handling, token validity, and expected behavior, which are critical for safe 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?

Schema coverage is 0%, so description must compensate. It states units (mm) for dx and dy, and notes the confirm_token requirement. However, it does not explain the coordinate system (e.g., relative vs absolute) or how to obtain the token, which would add significant 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 that the tool moves by dx, dy in mm, as indicated by '[MOVE] Desloca dx,dy mm'. The verb 'Desloca' (move) and resource (mm increments) are specific. However, it does not differentiate from sibling tools like 'arm_motion' or 'home_device', leaving some ambiguity.

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 a prerequisite (calling arm_motion('jog', ...) to obtain a token) but gives no guidance on when to use this tool vs alternatives, nor any exclusions or context about 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?

The description indicates the tool verifies a hash and refuses if tampered, which adds behavioral insight. However, no annotations are provided, and the description omits other behaviors such as side effects, permissions, or error states.

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, using a single sentence to convey the core purpose. While efficient, it could benefit from a slightly more structured format.

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 tool with 2 parameters and no output schema, the description is insufficient. It lacks explanation of what 'profile' and 'hash' refer to, and does not cover parameter purposes or expected outcomes.

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% description coverage, and the description does not mention any parameters or their roles. This fails to compensate for the lack of schema 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 verb 'load' and the resource 'profile', specifying it is the LOCKED profile and includes the action of verifying the hash. This distinguishes it from siblings like 'lock_profile'.

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. While the context of siblings exists, the description itself provides no usage context, when-not to use, or 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 must fully convey behavior. It mentions SHA-256 hashing, immutable writes, and a refusal mechanism for uncalibrated states. While these are important, it lacks details on destructiveness, return values, or error conditions.

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, using concise phrases. It is front-loaded with the core action and conditions, though it could be more structured for clarity.

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

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

Given four parameters, no output schema, and no annotations, the description lacks crucial context such as return values, side effects, and parameter purposes. It fails to compensate for the missing structural details.

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 four parameters but zero descriptions. The tool description does not mention any parameters or their roles, so it adds no meaning beyond the basic schema information (names, types, defaults).

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 locks (freezes) a profile including master, toolpath, calibration, and firmware, using SHA-256 and writing immutably. It effectively communicates the primary action and resource, distinguishing it from siblings like 'load_profile' which likely loads rather than locks.

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 notes that it refuses uncalibrated states, implying a precondition. However, it does not explicitly state when to use this tool versus alternatives like 'load_profile' or 'compile_calibrated', leaving the usage context somewhat implied.

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 discloses best-effort nature and that reproving blocks approval while passing does not approve alone. This adds some behavioral insight but lacks details on side effects, prerequisites, or state changes.

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?

Extremely concise (two sentences) but the first sentence is cryptic and the structure is not front-loaded with clear purpose. Could be clearer without adding length.

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

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

Given 3 parameters, no output schema, and no annotations, the description is incomplete. It does not explain inputs, outputs, or prerequisites. The behavioral hints are insufficient for full understanding.

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

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

Schema description coverage is 0% and description does not explain any of the three parameters (tol_mm, scan_path, signature_id). No additional meaning beyond the schema is 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 states it measures deviation between scan and master, but the phrasing is cryptic and unclear about the exact meaning of 'scan×mestre'. It distinguishes from sibling tools which are about calibration and motion, so purpose is somewhat clear but could be improved.

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 vs alternatives. It mentions behavioral effects like reproving blocking approval but does not compare to other tools or specify context.

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

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

With no annotations, the description must fully disclose behavioral traits. It mentions the actions 'park seguro' and 'recolhe a caneta', but does not disclose whether the action is irreversible, destructive, or requires specific preconditions. Missing critical details for a potentially destructive 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 sentence with no unnecessary words. It efficiently conveys the core action and a brief note on what happens (park and retract). No fluff.

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 lack of output schema and annotations, the description should cover prerequisites, side effects, and return behavior. It only provides a minimal action description, missing important context for a destructive tool with one required 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?

Schema description coverage is 0%, so the description should explain parameters. It does not describe the job_id parameter beyond its name in the schema. The description only says 'Aborts a job', which implicitly involves job_id, but adds no additional meaning.

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 'Aborts' and the resource 'a job', and adds specific details about what the abort entails ('park seguro + recolhe a caneta'). It is distinct from siblings like production_pause, but does not explicitly differentiate them.

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 like production_pause or production_run. The context implies it is for cancelling a job, but no when-to-use or when-not-to-use instructions are 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 present, so the description carries full responsibility. It discloses that pausing involves a 'safe park' and 'pen lifted' behavior, which is useful. However, it does not mention side effects, prerequisites (e.g., if job must be running), or whether it is idempotent. Adequate but not detailed.

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 immediately states the main action and behavior. No filler or redundant information. Every word is meaningful.

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 pause tool with one parameter, the description covers the basic action and immediate behavioral consequence. However, it lacks parameter explanation and any mention of return values or error states, leaving some gaps. Given no output schema, it is moderately 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 0%, so the description must explain parameters. It does not mention the job_id parameter at all—no format, source, or how to obtain it. The description adds no value beyond the schema's name and type.

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 pauses a production job and specifies it does a safe park with pen lifted. This is a specific verb+resource combination that distinguishes it from sibling tools like production_abort or production_resume.

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

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

No explicit when-to-use or when-not-to-use guidance is provided. However, the sibling tool names (production_abort, production_resume) imply that this is for temporary halting, not cancellation. Usage context is only implied, not stated.

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, and the description does not disclose behavioral traits such as idempotency, error behavior when job is not paused, or response format. The agent gets minimal insight beyond the basic 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 sentence, which is concise, but it lacks structure and additional details that could aid understanding. It is not overly verbose, but could benefit from more 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 one parameter, no output schema, and no annotations, the description should compensate by explaining return values, error conditions, or usage context. It does not, leaving the agent underinformed about 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 parameter 'job_id' has no description in the schema and is not mentioned or explained in the tool description. With 0% schema coverage, the description fails to provide any additional meaning, leaving the agent with only the parameter 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 it resumes a paused job ('retoma um job pausado') and provides a specific note about 'resume-from-stroke-N', indicating a specific variant. It distinguishes from sibling tools like production_pause and production_run through its verb and context.

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, no prerequisites (e.g., job must be paused), and no exclusion criteria. The description only defines the action without usage context.

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 bears full responsibility. It hints at refusal conditions ('Recusa sem LOCKED+hash+origem') and a call to arm_motion, but does not explain side effects, destructiveness, or auth requirements. The behavior is opaque.

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 short but not concise in a helpful way; it is cryptic and poorly structured, mixing natural language with pseudo-code without clear organization. Every sentence should be earned; here the single sentence is confusing.

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, no annotations, and a cryptic description, the tool is severely underdescribed. It fails to explain prerequisites (like LOCKED state), error conditions, return values, or how it fits into the production workflow.

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%. The description does not explain any parameter meanings (e.g., copies, profile_id, confirm_token). The cryptic line 'arm_motion('production_run',{profile_id})+token' does not clarify the 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 is cryptic and in Portuguese, mentioning 'Replica o perfil travado (background)' but not clearly stating the tool's purpose in English. The title is null, and the description does not differentiate from sibling tools like arm_motion.

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. Mentions 'arm_motion' but doesn't clarify the relationship or provide exclusions. The description lacks context for an AI agent to decide when to invoke.

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 should disclose side effects, permissions, or state changes. It mentions 'pré-condição da trava' (precondition of lock) but does not explain what happens upon approval or rejection, or any required authorization.

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 short (one line) but lacks structure. While concise, it does not front-load key information or provide a clear breakdown. The use of Portuguese and an arrow reduces 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?

For a tool with 4 parameters and no output schema or annotations, the description is insufficient. It fails to explain what the tool returns, preconditions, or postconditions, 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?

Schema description coverage is 0%, and the description does not elaborate on any parameters. The required 'signature_id' and 'approved' are only hinted by name, while 'scan' and 'notes' are completely unexplained.

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

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

The description states a human sign-off on a test plot, which aligns with the tool name 'record_test_result'. However, the phrasing is in Portuguese and uses an arrow notation that may be unclear. It vaguely distinguishes from siblings like test_plot but lacks explicit action specification.

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 such as test_plot or measure_fidelity. The description implies it is used after running a test plot but does not state prerequisites or exclusions.

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

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

With no annotations provided, the description must convey behavioral traits. It suggests a pre-hardware simulation ('pré-hardware') but does not clarify side effects, whether it is read-only or destructive, or what happens after invocation. The agent lacks understanding of the tool's impact.

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 (one short sentence) but at the cost of clarity. It is not front-loaded with key information and provides minimal value. Every word is present, but the sentence does not earn its place due to vagueness.

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 lack of annotations and output schema, the description is severely incomplete. The tool has 2 parameters and complex sibling relationships, yet the description offers no context about return values, side effects, or prerequisites. It is insufficient for correct agent invocation.

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

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

The description does not mention any parameters. With 0% schema coverage and two parameters ('out_dir', 'signature_id') that have no descriptions in the schema, the description fails to add any meaning. The agent cannot infer the role of these parameters from the 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?

The description 'Proof honesto pré-hardware (geometria/ordem/direção=REAL; largura=NOMINAL)' is cryptic and fails to clearly state what the tool does. It hints at a pre-hardware proof with specific geometric attributes, but the term 'proof' is ambiguous, and no resource or action verb is clearly defined. It does not distinguish this tool from siblings like 'compile_toolpath' or 'test_plot'.

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 'compile_calibrated' or 'production_run'. No prerequisites, context, or exclusions 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 discloses that the tool does not move the device, which is a key behavioral trait. With no annotations, it does not reveal what exactly 'captures' means (e.g., saves, affects other settings).

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 (two sentences) and front-loads the purpose. It earns its place but could be more 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?

With no output schema, no annotations, and undocumented parameters, the description lacks sufficient information about return values, side effects, or parameter usage.

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

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

Schema coverage is 0% and the description does not explain the two parameters (a4_ref_x, a4_ref_y) or their defaults, leaving the agent without guidance on how to specify them.

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 captures the paper origin from the current position and clarifies it does not move. However, it does not explicitly differentiate from sibling tools like calibrate_pen_paper or jog.

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

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

The description provides explicit pre-condition instructions: position the device to the bottom-left corner of the A4 plot area before calling. It lacks explicit when-not-to-use or alternatives.

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

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

No annotations exist; description provides minimal behavioral info. It implies motion ('MOVE'), but does not disclose side effects, required permissions, or device implications beyond requiring a confirm_token.

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 short but under-specified. The cryptic code string does not aid clarity and wastes space. Overly minimal for an 8-parameter tool.

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?

Tool is complex (8 parameters, no output schema, no annotations) yet description offers almost nothing. Return values, error cases, and parameter interactions are completely 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 0% and description adds no parameter meanings. Agent has no understanding of what values like 'accel', 'pen_pos_up', or 'pen_delay_down' represent.

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 in Portuguese states it adjusts pen positions/forces, but the inclusion of cryptic code 'arm_motion('set_pen_positions',{})+token' confuses the purpose. No explicit differentiation from sibling tools like 'test_pen_toggle' or 'calibrate_pen_paper'.

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. No prerequisites, exclusions, or context 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?

The description only states that toggling occurs, with no annotations to supplement. It does not disclose whether the action is destructive, requires confirmation, or has side effects. The code snippet hints at a token requirement but lacks clarity.

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 short and includes a code snippet, which may aid developers but adds unnecessary detail. It is front-loaded with the action but could be more focused on explanation rather than code.

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 parameter, no output schema) and lack of annotations, the description should provide more context about the toggle behavior, prerequisites (e.g., calibration), or typical use cases. It is insufficient for an agent to use 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 single parameter 'confirm_token' has no schema description (0% coverage). The description mentions a token in the code snippet, but does not explain its purpose, format, or how to obtain it. This adds minimal value 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 'Cicla a caneta cima/baixo' clearly indicates a toggle action for the pen up/down. The verb 'Cicla' (cycles) combined with the tool name 'toggle' conveys the purpose. However, it does not differentiate from sibling tools like arm_motion, which might handle related movements.

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 arm_motion. There is no mention of prerequisites, context, 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 provided, so description must convey behavior. It mentions 'MOVE' and 'job background' but doesn't disclose effects (e.g., if it overwrites, requires calibration, or any side effects). The token suggests a confirmation step but not detailed.

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 but not concise—it's cryptic and includes code-like fragments. It could be more structured and front-loaded with a clear action statement.

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

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

For a tool with 2 required parameters and no output schema, the description lacks completeness. It doesn't explain prerequisites (e.g., calibration needed), return values, or the confirmation token's role. Sibling tools suggest this is part of a setup workflow, but no context is provided.

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%. The description only hints at signature_id and token but does not explain their purpose or constraints. The token part is obscure (arm_motion(...)+token). No added meaning beyond the parameter titles.

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 mentions 'Plota o toolpath calibrado' (plot calibrated toolpath) but is written in Portuguese and unclear. It references arm_motion but doesn't clearly state what the tool does in English. The verb 'plot' gives a hint, but the resource and scope are ambiguous.

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 siblings like arm_motion or calibrate_pen_paper. The description assumes context (e.g., job background) but doesn't provide explicit when-to-use or when-not-to-use information.

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