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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is covered. The description still adds genuinely useful behavior: parent directories are auto-created, and existing files are overwritten without warning. It omits details like atomicity or encoding, but that is a minor gap against annotation coverage.

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 action, then three tight bullets that each carry real information. The only structural quibble is that 'Use absolute paths' is a parameter constraint placed among behavioral bullets, slightly misgrouped.

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 tool with no output schema, the description covers the key agent-relevant facts: side effects, path requirement, and overwrite semantics. Return/error behavior is not described, but no output schema exists to carry it, so this is a small residual 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 coverage is 100% and the schema already documents both 'path' (absolute path) and 'content'. The description's 'Use absolute paths' merely reinforces the schema's own wording rather than adding new meaning, so the baseline 3 applies.

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+resource ('Create or overwrite a file with the specified content'), which is far more informative than the bare name/title 'Create'. It does not explicitly differentiate from the sibling editing tools (str_replace, insert), 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?

'Create or overwrite' implies the write case, and 'Use absolute paths' gives a concrete usage constraint. However, it never says when to prefer this over str_replace or insert for modifying existing files, so the alternative-selection guidance is only 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?

Annotations already declare readOnlyHint=false and destructiveHint=true, so the safety profile is covered. The description adds operational conventions (newline termination, absolute paths) but says nothing about in-place mutation consequences, whether the file must already exist, or how out-of-range line values are handled — context that matters for a destructive write.

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 purpose is front-loaded in the first sentence and the remaining lines are tight bullets that each carry distinct information. No sentence 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 3-parameter mutation tool with annotations covering safety and no output schema, the description covers positioning, path form, and text formatting adequately. Minor gaps remain around failure modes (non-existent file, out-of-range line) and what the tool returns.

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 all three parameters are already documented, including the 0/-1 line mapping and the newline note. The description largely restates the schema's parameter descriptions rather than adding format, boundary, or error semantics beyond them, so the baseline 3 applies.

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 gives a specific verb+resource ('Insert text at a specific line in a file') and the line-index semantics make it operationally distinct from 'create' (new file) and 'str_replace' (in-place substitution). It does not explicitly name any sibling, so an agent must infer the boundary rather than being told it.

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 through the insert_line mapping (0=beginning, N=after line N, -1=end) and the absolute-path convention, which tells the agent how to position an insertion. However, there is no statement of when to choose this tool over str_replace or create, and no prerequisite or exclusion guidance.

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 flag destructiveHint=true and readOnlyHint=false, so the mutation warning is covered. The description goes beyond that by disclosing the failure mode (ambiguous or absent match aborts the operation) and the deletion semantics of an omitted new_str - real behavioral detail an agent needs before calling.

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?

Four tight bullets, front-loaded with the core action, zero filler. Every line carries actionable constraint 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?

With no output schema, the description should ideally say what a successful call returns or how the change is reported, and that gap remains. Otherwise the preconditions, failure modes, and path requirement make it complete enough for correct 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?

Schema description coverage is 100%, so the schema already documents path, old_str (unique match) and new_str (omit to delete). The description largely restates that information rather than adding syntax, format, or encoding details, so the baseline 3 applies.

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 ("Replace an exact string in a file") and adds behavioral specifics. It distinguishes itself from `view` and `create`, but never explicitly differentiates from the `insert` sibling, which an agent could plausibly confuse with string replacement.

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 states operational preconditions clearly (exact unique match required, failure on 0 or >1 occurrences, omit new_str to delete, use absolute paths), which is genuinely useful. However, it gives no guidance on when to choose this tool over `insert`, and no exclusions or alternatives are named.

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 readOnlyHint annotation by disclosing the exact truncation limit (16000 characters), the line-number output format, the default directory depth (2 levels), and the ignore rules (hidden files, node_modules). These are precisely the behaviors an agent must know before calling.

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-loads the one-line purpose, then splits the two modes into short, scannable bullet groups. Every bullet carries operational detail (format, range semantics, truncation, depth, ignores) with no filler.

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 description carries the return-format burden and does so for both modes, including line-number formatting, directory type indicators, depth, and truncation. An agent has everything needed to call it 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%, so both parameters are already documented with the same 1-indexed inclusive semantics. The description restates view_range's behavior and adds the line-number output format, which is useful but not much beyond the schema baseline.

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 (view file contents or list a directory) with the two modes spelled out. The sibling set is entirely mutating (create, str_replace, insert), so this read-only tool is trivially distinguishable.

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 clear branch conditions: file vs directory, and explicitly says to use view_range for reading specific lines. It does not name an alternative tool or state exclusions, but the read-vs-write split against its siblings is unambiguous.

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