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

Annotations already declare readOnly, idempotent, and non-destructive behavior. The description adds 'Pure analytical evaluation with no side effects,' which reinforces and clarifies the tool's behavior without contradicting the annotations. No additional behavioral surprises are hidden.

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

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

The description is three sentences, front-loads the core purpose, includes usage timing, and ends with a side-effect guarantee. Every sentence earns its place and there is no redundancy.

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

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

With one fully documented parameter, robust annotations, an output schema present, and clear phase-based usage guidance, the description covers everything an agent needs to select and invoke this 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?

Schema description coverage is 100% and the single parameter brief_text is already described as 'Markdown content of the architectural intake brief to evaluate.' The description adds no new parameter-level detail, so the baseline of 3 is appropriate.

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

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

The description uses a specific verb ('Evaluate') with a clear resource ('architectural brief') and names concrete evaluation criteria (determinism rules, invariant floors, ACI 1.0000). It is clearly distinguishable from siblings like prune_file and resolve_context_bundle.

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 states exactly when to use the tool ('during intake or planning phases before writing code'), giving clear temporal context. It does not explicitly enumerate when not to use it, but the stated phase guidance is sufficient for typical routing.

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, destructiveHint=false, and idempotentHint=true. The description adds the crucial detail that it is a 'pure in-memory AST operation' and does not modify files, which reinforces the read-only nature. It also explains the stubbing behavior ('replacing procedural bodies with AST stubs'), a behavioral trait not captured by annotations. No contradictions with 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 three sentences: the first states what it does, the second gives a usage condition, and the third clarifies safety. It is front-loaded with the core behavior and has no filler. It could be slightly tightened ('pure in-memory AST operation' is mentioned both implicitly and explicitly) but remains efficient and well-structured.

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

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

With an output schema present, the description does not need to document return values. The tool has moderate complexity (4 parameters) but the schema covers them all. The description covers purpose, usage, and safety assumptions. Missing are potential edge cases (e.g., unsupported language, invalid path), but these are not essential for basic selection and invocation. A 4 reflects sufficiency without exhaustive detail.

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

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

Schema description coverage is 100%, so every parameter (path, depth, language, strip_docs) has a descriptive comment. The description does not add additional parameter-specific meaning beyond the schema, but the baseline for high coverage is 3. It neither improves nor detracts from the schema, so a 3 is appropriate.

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

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

The description clearly states the tool's function: extracting semantic interfaces, types, models, raises, and signatures while stubbing bodies. It names specific output artifacts and contrasts with 'ingesting raw implementation code,' making its purpose precise. The sibling tools (resolve_context_bundle, evaluate_spec_axioms) are distinct enough that no further differentiation is needed.

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

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

The description explicitly says 'Use this when you only need to inspect contracts or APIs of an individual dependency without ingesting raw implementation code.' This gives a clear condition for use. It does not explicitly name alternatives or say when not to use it, but the context is sufficient for an agent to decide. A 4 reflects the strong 'when' but lack of explicit 'when-not' or named 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?

The annotations already cover read-only, idempotent, and non-destructive behavior, so the description does not need to restate safety. It adds meaningful behavioral context beyond annotations by specifying the D0/D1/D2 distance levels and the token-pruned Markdown output format. The 'Read-only operation' sentence is redundant with annotations but not contradictory.

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

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

Three sentences with no wasted words. The core function is front-loaded, usage context follows, and the alternative tool is named in the final sentence. The only minor redundancy is 'Read-only operation,' but it is one short clarifying phrase.

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 read-only context-building tool with full schema description coverage and an output schema, the description covers purpose, usage timing, alternatives, and output format. An agent has all necessary information to decide when to call it and what to expect from it.

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

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

Schema description coverage is 100%, so the schema already documents both target_file and project_root. The description reinforces target_file's role as the active target file but adds no new parameter-level meaning, such as how project_root affects traversal or what values are valid.

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-resource pair: it calculates topological dependency graph distances and compiles a token-pruned Markdown context bundle. It also differentiates itself from prune_file by framing itself as the primary context builder, so an agent can select it confidently without inspecting siblings.

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 explicit when-to-use guidance: 'primary context builder before editing a file in a multi-module project.' It also names the alternative for isolated files: 'use prune_file instead.' This is direct, actionable routing guidance.

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