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

Annotations already declare read-only, idempotent, non-destructive, but the description goes further: it confirms no auth, no rate limits, no file overwrites, and describes both return paths (OK string with isError=false, versus isError=true with per-violation findings and remediation prompts). That is materially beyond what the annotations convey.

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?

Front-loaded with the guard names and trigger patterns, then usage rules, then parameter and return behavior in a logical order. It is dense but every clause carries signal; only the triple enumeration of guard internals makes it longer than strictly necessary.

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 single-parameter, non-mutating check with no output schema, the description covers invocation fallback, success/failure semantics, and remediation behavior. Nothing an agent needs to call it correctly 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?

With one optional parameter and 100% schema description coverage, the baseline is 3. The description explains diff_text versus the fallback to git diff HEAD, but the schema already documents that same fallback almost verbatim, so it adds little beyond structured data.

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 (Verifies) and resource (code snippet or git diff) and enumerates all three named checks with their trigger conditions. It explicitly distinguishes itself from siblings vicem_read_baton and vicem_rehydrate, so an agent can route correctly without opening any schema.

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 states when to use ('before committing or finalizing edits to skeletonized files') and when not to use, naming the two sibling alternatives and the condition that selects each. This is exactly the when/when-not/alternatives pattern.

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?

Goes well beyond the annotations: names exactly which files are overwritten (.vicem/BATON.md, baton.json, ledger.json), that overwrite is idempotent, that a rollback snapshot is written to .vicem/snapshots/ first, that secrets are redacted, and that no source files are mutated. It also states there are no auth or rate limits, which is real operational context. This is consistent with destructiveHint=false and idempotentHint=true — no contradiction.

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?

Purpose is front-loaded and the sentences are dense with useful detail rather than filler. It is long, and the closing note about return value and isError=false adds little for a tool with no output schema, slightly diluting the close.

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?

Only three optional parameters and no output schema, yet the description covers the return value, the destructive-safety story, secret handling, and the meaning of every parameter. An agent has everything needed to invoke it correctly without opening anything else.

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 earns above that by explaining effect: goal overrides auto-extracted session intent specifically in Section 1, targetAgent tailors receiver instructions (default codex), and budgetTokens governs skeletonization depth. That causal detail is not in the schema descriptions, though the Tier 3/4 terminology is left 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?

Opens with a specific verb and resource pair: 'Creates a compressed U-Shaped Context Baton (.vicem/BATON.md) and symbol ledger (.vicem/ledger.json) from the current project session and git state.' The scope (session + git state) and artifacts are named concretely, and it explicitly differentiates itself from vicem_read_baton, vicem_rehydrate and vicem_check_guard.

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?

Gives an explicit trigger ('at session end or before quota limits to hand off work') and an explicit exclusion list mapping each negative case to the correct sibling tool. Nothing is left to inference about when to pick this tool over the three 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?

Beyond the read-only and non-destructive annotations, it discloses that the operation is local with no auth, rate limits, or file mutations. It also explains the return behavior: full BATON.md text with isError=false, a staleness drift warning banner with both commit hashes when git HEAD has moved, and isError=true when the file is missing.

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 front-loaded with the core action and usage condition, then adds exclusions and behavioral details in a compact sequence. Despite covering several important behaviors, every sentence contributes necessary selection or invocation 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?

There is no output schema, but the description fully explains return values, error behavior, and the drift warning. Together with annotations covering safety and locality, it gives an agent everything needed to invoke and interpret the tool correctly.

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

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

The tool takes zero parameters, so there are no parameter semantics to clarify; the baseline for zero parameters is 4. The description does not need to compensate for any parameter documentation gaps.

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 specific verbs and resources: it reads the current .vicem/BATON.md handoff document and checks git HEAD drift against .vicem/baton.json. It also distinguishes itself from the sibling tools vicem_create_baton, vicem_rehydrate, and vicem_check_guard.

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 explicitly says to use this first when starting a handed-off session and lists what not to use it for, naming the alternative tool for each excluded action. This leaves no ambiguity about when to select this tool versus its siblings.

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 readOnly/idempotent/non-destructive, but the description adds substantial context beyond them: no auth, rate limits, or disk writes; returns redacted source; prepends a STALENESS DRIFT WARNING when git HEAD or the file changed; and returns isError=true with a not-found message when the symbol is absent or not skeletonized.

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?

Front-loaded with the core purpose and alternative routing before a labeled 'Parameter semantics' block. It is dense but every clause carries information; length is justified by the amount of behavioral detail packed in, though it borders on over-packed for a single paragraph.

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

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

Despite no output schema, the description fully covers return values, success/error signaling, and staleness handling, so an agent knows exactly what to expect. Nothing needed for correct invocation or result interpretation 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 coverage is 100%, so parameter baselines are already met, but the description adds value by noting path-traversal validation on file_path, the requirement that symbol_name match a ledger entry, and acceptance of camelCase filePath/symbolName aliases. This is meaningfully more than the schema 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?

States a specific verb and resource: 'Restores the exact, secret-redacted source code of a skeletonized function, method, or class from .vicem/ledger.json.' It names the exact artifact and the source of truth, making it immediately distinguishable from siblings like vicem_read_baton or vicem_check_guard.

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 when to use it ('after vicem_read_baton whenever you need to inspect or edit a symbol listed in Section 6') and lists three concrete do-not-use cases mapping to each sibling. Routing is unambiguous.

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