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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds the 'bounded set' and 'before adding an abstraction' context but does not disclose return format or result behavior, which is acceptable given the annotations.

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 filler. It front-loads the core action and resource while adding the key workflow context.

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 read-only search tool, the annotations cover safety and the description covers scope and timing. There is no output schema, but the tool's role is clear enough that missing return-format details are a minor gap.

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

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

Schema description coverage is 0% and the description adds no explicit parameter guidance. The query and limit parameters are inferable from their names and schema constraints, but the description does not explain semantics beyond what the input schema already provides.

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

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

The description states a specific verb and resource: 'Search a bounded set of source files'. It also gives the purpose, 'before adding an abstraction', which distinguishes it from the sibling tools that validate, review, or prepare changes.

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 clearly frames when to use this tool: before adding an abstraction. It does not explicitly name alternatives or exclusions, but the temporal condition is enough to route an agent toward this discovery step.

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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context by naming the content the tool gathers, but it does not disclose output format, limitations, or side effects beyond what annotations already imply.

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 one efficient sentence with no wasted words. It front-loads the main action and resource, though the phrase 'one coding request' is slightly awkward and the sentence could have been more direct.

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?

There is no output schema, and the description does not explain what the tool returns, how to use the returned context, or how the two parameters relate. The mention of repository structure, patterns, and architecture rules gives some sense of the gathered content, but important operational 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%, and the description does not explain the 'query' or 'request' parameters at all. The word 'request' in 'coding request' gives a weak hint, but 'query' remains completely ambiguous. With no parameter explanation in either the schema or the description, the agent cannot confidently know how to fill these fields.

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

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

The description states a specific action ('Prepare') and a resource ('one coding request'), and it clarifies what that preparation includes: repository structure, existing patterns, and architecture rules. This helps distinguish the tool from sibling tools that handle those concerns individually, though 'prepare' remains somewhat abstract.

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

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

The phrase 'in a single call' implies this tool should be used to combine multiple context-gathering steps that siblings like aplomo_understand_repo and aplomo_find_existing_patterns perform separately. However, there is no explicit guidance about when to choose this tool over those alternatives or when 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is well covered. The description adds the context of summarizing both configuration and repository structure, which is useful but not a significant behavioral disclosure beyond what annotations imply. Given the strong annotation coverage, a 3 is appropriate.

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

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

The description is a single, well-structured sentence that immediately states the action and purpose. It is front-loaded with the core verb and resource, contains no filler words, and every part earns its place. This is an example of efficient, high-quality writing.

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 that there are no parameters, no output schema, and annotations cover the safety profile, the description is largely complete. It clearly indicates the tool produces a summary of architecture configuration and repository structure, which tells the agent what to expect. While it could specify the format of the summary, this is a minor gap for a zero-parameter summarization 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 tool has zero parameters, so the schema is empty. The description does not need to elaborate on parameters, and the baseline for 0-param tools is 4. There is no additional parameter information required, and the description adequately communicates the tool's purpose without referencing 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 action 'Summarize' and the specific resources 'architecture configuration and repository structure' with a clear purpose 'for an architecture review'. This distinguishes it from siblings like review_plan (which reviews a plan) and review_diff (which reviews a diff), making it easy for an agent to select the correct tool.

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

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

The description provides clear context by stating it is for an architecture review, implying when it should be used. However, it does not explicitly mention when not to use it or point to alternative tools such as understand_repo or find_existing_patterns, which might also be relevant in similar contexts. This falls short of a 5 but is still clear enough for typical usage.

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?

Annotations already declare readOnlyHint, destructiveHint, and idempotentHint, covering the safety profile. The description adds that it reviews for specific categories, which is more purpose than behavioral disclosure. No additional side effects or constraints are mentioned, so it adds marginal value beyond annotations.

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 immediately states the action and scope. There is no filler or redundancy; every word earns its place.

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

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

For a tool with no parameters, clear annotations, and no output schema, the description adequately covers what the tool does. An agent can correctly call it without further information. Nothing essential 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?

There are zero parameters, so the schema is trivially complete (coverage 100%). The description does not need to explain parameters, and the baseline for 0-param tools is 4. It does not add extra parameter info, but none is needed.

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

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

The description uses a specific verb ('review') and resource ('current git diff'), and specifies the exact concerns (risky size, secrets, missing test changes). It clearly distinguishes from siblings like review_plan and review_architecture, which focus on different artifacts.

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

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

The phrase 'current git diff' gives clear context that this tool is for reviewing the diff, which implies the appropriate use case. However, it does not explicitly state when not to use it or mention alternatives, so it falls short of a 5.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the read-only safety profile is covered. The description adds the evaluation criteria but does not disclose behavior such as output format, side effects, or how results are presented, which keeps this at a mid-level score.

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

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

The description is a single sentence, front-loaded with the core action and resource, and contains no filler or redundant wording. Every word contributes to the meaning, making it appropriately concise.

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

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

The tool is simple with one parameter and safety is covered by annotations, so the basics are present. However, there is no output schema and no mention of what the tool returns (e.g., a pass/fail verdict or a list of missing items), and no usage context relative to siblings, leaving meaningful 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?

The input schema provides no description for the 'plan' parameter (0% coverage), but the tool description clarifies that it represents an implementation plan and enumerates the aspects it should cover. For a single self-named string parameter, this adequately compensates for the missing schema documentation, though input format is not specified.

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 identifies a specific resource, 'implementation plan', and lists the criteria being checked: patterns, scope, compatibility, and validation. This distinguishes it from siblings like review_diff or review_architecture, though the verb 'Check whether' is somewhat generic and it does not explicitly differentiate itself from other review 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 gives no guidance on when to use this tool versus alternatives. It does not reference any sibling tools, prerequisites, or exclusions, leaving the agent to infer the appropriate context 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, and the description does not contradict these. However, the description adds no behavioral context beyond the basic action—no mention of scope limits, cost, auth, output shape, or whether it analyzes only local code versus external references.

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 11-word sentence that front-loads the main action and contains no filler. Given the zero-parameter surface, this level of brevity is appropriate.

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

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

The tool is simple, with no parameters and full annotation coverage, and the description conveys its purpose. Still, it does not indicate what the output looks like (list of technologies? symbol summaries? structure), and there is no output schema to compensate, so the definition is only minimally complete.

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

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

The input schema has zero parameters and schema description coverage is 100%, so there is no missing documentation for the description to supply; the no-parameter baseline is 4.

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

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

The description uses action verbs 'Detect' and 'summarize' and clearly scopes to 'modules and symbols in the repository.' It is immediately clear what the tool does, though it does not explicitly contrast itself with sibling analysis tools such as aplomo_find_existing_patterns or aplomo_review_architecture.

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

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

There is no explicit statement about when to invoke this tool versus alternatives. The wording simply restates the tool's function; an agent would have to infer that repository reconnaissance is a prerequisite to the planning/review siblings, which is 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds the core evaluation criterion — reuse or responsibility/lifecycle justification — as behavioral context for what makes an abstraction acceptable. It does not describe the outcome format or rejection behavior, but the annotations reduce the need for mutation/side-effect 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 a single front-loaded sentence with no filler or repetition. It delivers the core policy in a compact, scannable form and every word contributes to meaning. The brevity is a strength, even though some of that brevity creates ambiguity elsewhere.

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, the agent cannot tell whether validation returns a boolean, an explanation, or an error. The phrase 'lifecycle justification' is undefined, and the relationship between the 'reuse' criterion and the required 'responsibility' parameter is left unclear. For a validation tool, the pass/fail behavior is essential missing 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%, so the description must compensate for explaining parameters, but it only loosely maps to them. It mentions 'responsibility/lifecycle justification' without clarifying the required 'responsibility' field or the optional 'justification' field, and it never explains 'proposed_name' or how 'reuse' maps to a parameter. This is insufficient semantic help for an agent invoking the tool.

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 an explicit policy gate: 'Require reuse or an explicit responsibility/lifecycle justification before adding an abstraction.' This makes clear the tool validates or rejects abstraction proposals and distinguishes it from sibling review tools by focusing specifically on adding abstractions. It stops short of a 5 because the action verb is somewhat implicit and the description reads more like a rule than a behavioral 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?

The phrase 'before adding an abstraction' gives a clear temporal trigger for when this tool should be used. However, it does not name sibling alternatives or state when not to use it, leaving the agent to infer how this differs from aplomo_review_architecture or aplomo_review_plan. This is implied usage guidance rather than explicit routing.

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