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

With no annotations, the description carries the full behavioral burden. It discloses the key transformation (bodies replaced with '...') and token savings, but does not explicitly state read-only behavior, supported languages, parse-error handling, or permission requirements.

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 definition is two front-loaded sentences with no waste. The core extraction behavior comes first, followed by a compact token-efficiency rationale.

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 two-parameter extraction tool with no output schema, the description sufficiently explains the return shape as an AST outline with bodies elided. It could be slightly more complete by noting language support or failure behavior, but no critical invocation detail 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 100%, so both parameters are already documented. The description does not add meaning about path handling or how depth controls traversal beyond what the schema provides, making the baseline 3 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 ('Extract') and resource ('AST outline') and lists the exact elements returned: classes, functions, signatures, type hints, and docstrings. It clearly distinguishes this from raw file reading, but it does not name or differentiate against sibling tools such as symbol_slice.

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 token-efficiency claim implies the tool should be used when a compact code overview is needed, but there is no explicit guidance on when to choose it over symbol_slice or other siblings, and no when-not-to-use conditions.

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 supplied, so the description carries the full disclosure burden. It does explain the key behavioral trait that output is deliberately context-free (no unchanged surrounding lines) and stripped of git index boilerplate, which is valuable for an agent that may otherwise expect surrounding code. It omits permissions/read-only confirmation, truncation or size limits on large diffs, and behavior for untracked or binary files.

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 front-loaded sentence that leads with the verb and format and then explains the two compression effects. Dense and largely waste-free, though the parenthetical flag plus its prose restatement is slightly redundant for git-literate agents.

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 two-parameter, all-optional read tool with no output schema, the description covers the essential thing an agent needs: what the returned diff looks like (zero context, no boilerplate). Minor gaps around size limits and untracked files keep it from being exhaustive.

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 parameters, establishing a baseline of 3. The description's phrases 'uncommitted changes' and 'specific files' loosely map to the staged and filepath parameters but add no syntax, format, or default-override detail 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 names a specific verb and resource ('Generate a zero-context (-U0) git diff') and states its scope ('uncommitted changes or specific files') plus its distinguishing trait, the removal of context lines and index boilerplate. No sibling among code_skeleton, symbol_slice, smart_exec, test_compress or token_ledger offers a diff, so no explicit differentiation is needed, but the description also does not say how it relates to those token-saving 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?

Usage is implied rather than stated: it is for uncommitted changes, optionally narrowed to a single file. There is no indication of when to prefer it over other inspection tools, no note about untracked files, and no 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, the description carries the full burden, and it does disclose meaningful behavior: ANSI stripping, carriage-return collapse, progress/spinner suppression, and truncation of output. However, it omits critical operational facts for arbitrary shell execution — exit-code handling, stderr capture, timeouts, working directory, and permission/safety implications.

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 front-loaded sentence with the action first and the modifiers after — efficient and zero filler. The dense feature list is slightly jargon-heavy but every clause conveys distinct 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?

There is no output schema and no annotations, so the description should ideally state what comes back (stdout string? exit status? error text?) for a tool that runs arbitrary commands. It is thorough about output transformation but silent on return shape and failure semantics, leaving a real gap for an execution 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?

Schema coverage is 100%, so both parameters are already documented, making 3 the baseline. The description adds only marginal meaning: 'intelligent head/tail truncation' explains the strategy behind max_lines (preserving both ends rather than cutting the tail), but no format or interaction detail 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 opens with a specific verb+resource pair ('Execute a shell command') and then enumerates the output post-processing it performs. It is clearly distinguishable from the compression-oriented siblings (code_skeleton, diff_compact, test_compress), though it never explicitly names them or states how it differs from 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?

Usage is only implied: the emphasis on progress-bar/spinner suppression and head/tail truncation signals the tool is meant for noisy, long-running commands whose output would otherwise flood context. There is no explicit when-to-use, when-not-to-use, or alternative-sibling 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?

No annotations are supplied, so the description carries the full behavioral burden, and it discloses little. It says nothing about read-only nature, what happens when the symbol is missing or ambiguous (e.g. multiple 'charge' methods across classes), whether surrounding context or imports are included, or whether the output is raw source text.

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?

One sentence, front-loaded with the action and resource, with the examples and the rationale ('avoiding the need to read the entire file') doing useful work. Nothing is redundant.

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 two-parameter read tool with full schema coverage and no output schema, the description covers the core mechanics adequately. It leaves unresolved the failure and ambiguity cases an agent would want to know before calling, which is a meaningful gap even at this complexity level.

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 100%, so the baseline is 3, but the description genuinely adds meaning by demonstrating the accepted symbol syntax including qualified 'Class.method' form, which the schema's 'Name of the class, method, or function' does not convey. This is real value beyond the structured field.

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?

States a specific verb and resource — 'Extract the exact implementation of a single class or function by symbol name' — and gives concrete symbol forms ('PaymentGateway', 'PaymentGateway.charge', 'charge'). It does not name or contrast with the sibling code_skeleton, which likely overlaps in purpose, so it stops short of a 5.

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?

Usage is implied by the phrase 'avoiding the need to read the entire file', which signals the token-saving context and that you should already know the symbol name. There is no explicit when-not guidance and no alternative tool is named, so an agent must infer the boundary with code_skeleton.

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 behavioral burden; it does disclose the key output-shaping behavior (only failures, assertion errors, clean stack frames, passed tests collapsed to a one-line summary), which is valuable. It says nothing about execution side effects, timeouts, working directory, or exit-code semantics for a tool that clearly shells out to arbitrary commands.

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 front-loaded sentence that leads with the action and then the output contract; no filler or hedging. The framework enumeration is slightly redundant with the schema examples but still earns its place as a scoping signal.

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 one-parameter tool with no output schema and no annotations, the description covers both the input domain (test frameworks) and the return shape (failures plus a collapsed pass summary). Only execution environment details like timeouts or working directory are missing, which are secondary for this tool's core contract.

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 is only one parameter and schema coverage is 100%, with concrete example commands already in the schema, so the schema does the heavy lifting. The description's framework list marginally reinforces accepted values but adds no syntax or constraint information beyond what the schema documents.

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 ('Run test suites') and enumerates the exact frameworks supported (pytest, cargo test, go test, jest/vitest), so what it does is unambiguous. It does not, however, distinguish itself from the sibling 'smart_exec', which plausibly also executes commands, leaving overlap for the agent to resolve.

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?

Usage is only implied by the framing around test frameworks; there is no explicit statement of when to prefer this over 'smart_exec' or when it is inappropriate (e.g., non-test commands, interactive suites). The agent can infer intent from the examples but must guess at boundaries.

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 supplied, so the description carries the full disclosure burden. It does add real value by naming the three pieces of information returned, and by revealing the health zone is an enumerated GREEN/YELLOW/RED alert. However, it never explains what the zones mean, what thresholds trigger them, whether the call is free of side effects, or whether OCCE savings are per-session or lifetime.

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, with the primary subject (token usage) front-loaded ahead of the secondary metrics. The trailing parenthetical is slightly clunky but earns its place by enumerating the zone values.

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 zero-parameter read-only status call this is close to adequate, and the description compensates for the absent output schema by listing what comes back. It falls short on undefined terms ("OCCE") and on the semantics of the RED/YELLOW/GREEN zones, which an agent would need in order to act on the result.

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 takes zero parameters and the schema is fully covered, so there is nothing for the description to clarify. The baseline of 4 applies; no parameter-level meaning is missing.

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 concrete verb ("Check") and enumerates three specific resources: session token usage, cumulative savings from OCCE, and the free-model attention health zone. That is far more specific than the bare tool name. It loses a point because "OCCE" is unexplained jargon and the description does not position the tool against any sibling (code_skeleton, smart_exec, etc.), though those siblings are clearly unrelated.

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 when-to-use guidance, no preconditions, and no alternatives named. Usage is only weakly implied by the word "Check" (a monitoring/inspection call). An agent can guess this is a status check, but nothing tells it when monitoring is warranted or when to call this instead of other tools.

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