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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the agent knows this can overwrite. The description adds useful context not in the annotations — that binary files are supported and that the source lives in a staging folder — but says nothing about overwrite behavior at the destination, which is the main reason destructiveHint would be set.

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?

Two tight sentences front-loaded with the action, followed by compact per-parameter notes. No redundancy and nothing that fails to earn 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?

Output schema exists, so return values need no explanation, and annotations cover the safety profile. For a two-parameter copy tool the description is nearly complete; the only real gap is destination-overwrite behavior, which is left to the destructiveHint annotation.

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 carry parameter meaning, and it does: 'name' is explained as a bare name, sub-path, or full Windows path within the staging folder, and 'path' is tied to write_file's path rules. This meaningfully compensates for the empty 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?

States a specific verb and both endpoints of the operation: copy a file from the Windows staging folder (including binary) to a path in WSL. This cleanly distinguishes it from the sibling copy_to_windows, which moves in the opposite direction.

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?

Implies the context clearly — use this when you made a file in the Windows staging folder and need it inside WSL — and the 'same rules as write_file' reference ties path semantics to a known sibling. It stops short of an explicit 'use copy_to_windows for the reverse' statement, but the direction is unambiguous.

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?

Adds real context beyond the annotations: binary-file support, the existence and role of the staging folder, and the server-side precondition that the feature is disabled without one. Since destructiveHint=true, it would be stronger if it disclosed overwrite behavior when 'name' collides with an existing staged file, which is the main unstated risk.

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 and precondition are front-loaded in the first two sentences, and the parameter notes are compact. The two inline parameter lines are a slightly clunky structure but every line carries 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?

An output schema exists, so return values need not be described. Coverage of purpose, precondition, binary support, and both parameters is sufficient for correct invocation; only failure/overwrite behavior 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 0% schema description coverage the description must carry the burden, and it mostly does: 'path' is identified as the file in WSL, and 'name' is explained as a file name or sub/path inside the staging folder with the empty-default behavior spelled out ('empty keeps the file's own name'). Only the accepted path syntax (absolute vs relative, backslash vs forward slash) is left unaddressed.

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 (copy) plus the exact resource and direction: a WSL file into the Windows staging folder. It further narrows scope with binary formats (docx, pdf, png, .skill), which makes it trivially distinguishable from the sibling copy_from_windows and the read/write_file family.

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 usage context (use it so 'your own file tools can open' the file) and an explicit precondition: 'Off unless the server has a staging folder set.' It does not explicitly name copy_from_windows as the counterpart for the reverse direction, so routing is implied by naming rather than 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 destructiveHint=true and readOnlyHint=false, so the safety profile is covered. The description adds the non-obvious failure precondition that old_string must occur exactly once unless replace_all is true, which is real behavioral value beyond the annotations. It stops short of describing what happens on no-match/multi-match failure.

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 core behavior and the critical uniqueness rule in the first sentence, then uses four tight lines to define parameters. No filler or 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?

An output schema exists, so return values need not be explained, and the description covers the main error condition. Remaining gaps are minor: path format (relative vs absolute), behavior when old_string is absent, and the read-before-edit requirement are left implicit.

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 carries the full burden, and it defines all four parameters in prose. The 'without line numbers' detail for old_string is genuinely clarifying, though 'path: the file to change' adds little beyond the parameter name.

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 ('Replace exact text in a file') and the exact-match semantics imply it is a surgical edit rather than a full rewrite, which separates it from write_file. However, it never names or contrasts with its closest sibling write_file explicitly, so an agent must infer the boundary.

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 parenthetical '(copied from read_file output, without line numbers)' implies a read-then-edit workflow, which is useful. But there is no explicit when-to-use-this vs write_file guidance and no statement of preconditions such as the file needing to exist or have been read first.

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 and openWorldHint=false, so the safety profile is covered. The description adds useful matching behavior ('pattern without / also matches bare file names'; 'path empty means the first root') and the stopping condition, but says nothing about result ordering, error behavior on a missing path, or scoping beyond the first root.

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 lead sentence followed by one terse line per parameter; no filler, and the examples appear before the mechanics. The parameter lines are telegraphic but each still 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?

An output schema exists, so return values need no explanation, and all three parameters are documented in the description despite 0% schema coverage. What remains thin is error/edge-case behavior, which is minor for a read-only file finder.

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 carry the load and largely does: all three parameters are explained, including what the pattern is matched against, the meaning of an empty path, and what max_results truncates. It stops short of stating the default values or whether max_results counts matches or scanned entries.

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 ('Find files by name') and reinforces it with concrete glob examples ('*.md', 'docs/**/*.py'). An agent can distinguish it from content-oriented siblings like `search` or `list_dir` from the glob semantics, though no sibling is named explicitly.

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 clearly by the glob examples and the pattern-vs-path distinction, so an agent can infer that this is for name matching rather than directory enumeration. However it never states when to prefer this over `list_dir` or `search`, nor any exclusions or prerequisites.

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 cover the safety profile (readOnlyHint, openWorldHint=false), but the description adds genuinely useful behavior: recursion depth is capped at 1-5 and .git, node_modules, .venv and caches are deliberately not entered, which materially changes what an agent will see. Gaps remain on error handling (e.g. nonexistent path) and symlink behavior.

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 line of purpose followed by two compact parameter notes; front-loaded and every sentence adds information. No filler or restatement of the tool name.

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, return values need no explanation, yet the description still usefully documents result ordering. Both parameters are covered and the traversal exclusions are stated; the only shortfall is unstated failure behavior for bad paths or depths.

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 carries the full burden and largely meets it: path defaults to the first root (~/dev) when empty, and depth is bounded to 1-5 levels. Only the 'depth' interplay with the excluded-directory behavior and out-of-range values is unaddressed.

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 ('List a folder') and even specifies the output shape: subfolders first with trailing '/', then files with sizes. That distinguishes it from read_file and search, though it never explicitly names the closest sibling list_roots as a contrasting option.

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 — an agent can infer this is for browsing a directory tree rather than finding files by name. There is no explicit 'use this when... instead of find_files/search/list_roots' statement, so routing among the eight siblings is left to inference.

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 cover readOnlyHint=true and openWorldHint=false, so the safety profile is known. The description adds genuinely new behavioral context beyond the annotations: the tool defines an access boundary, and paths outside it are refused by the server — useful for predicting failure modes of sibling file tools.

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?

Two short sentences with no filler. The resource identification comes first and the constraining rule second, which is the correct front-loading for an access-boundary tool.

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?

An output schema exists, so return values need not be described, and there are no parameters to document. For a simple read-only enumeration the description covers what the list represents, though it could note whether the result set is static or configuration-dependent.

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 the baseline is 4. There is nothing parameter-wise for the description to compensate for, and schema description coverage is 100%.

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 the resource precisely — the server's permitted root folders — and the second sentence adds the boundary rule. It is clear what an agent gets back, though it lacks an explicit verb like 'list' and never names a sibling to contrast against.

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?

'Every other path is refused' implies this should be consulted before passing paths to read_file/write_file, but that inference is left to the agent. There is no explicit when-to-call or when-not-to-call statement, and no sibling is 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?

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds genuinely useful behavior beyond that: the returned line format ('<number><tab><text>') and the accepted path spellings (WSL absolute, Windows-style, or relative). It is silent on encoding, binary files, and error behavior for missing paths.

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 short, front-loaded sentences: the core action and output shape first, then one line per parameter. No filler, no restatement of the tool name.

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?

An output schema exists, so return-value documentation is not required, yet the description still states the line-numbering format, which helps the agent parse results. Given the tool's simplicity, the only meaningful omissions are default values and failure behavior for non-existent or unreadable files.

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 carry the burden and it does: path lists the accepted path forms, offset is defined as 1-based line numbering, and limit is defined as a line count. Every parameter gets meaning beyond its bare name, fully compensating for the empty schema descriptions.

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 ('Read a text file') and immediately specifies the output format, so the operation is unambiguous. It does not explicitly contrast itself with siblings like write_file, edit_file, or search, but the verb makes the distinction obvious.

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 'Read a text file' and by the offset/limit paging semantics, which tell the agent how to read a slice rather than the whole file. There is no explicit when-to-use/when-not guidance, no mention that this is unsuitable for binary files, and no pointer to search or find_files for locating content.

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 and openWorldHint=false, so safety is covered structurally. The description adds the match-line output format and max_results truncation behavior, but says nothing about recursion depth, performance cost beyond the 'large' aside, or error behavior on bad regex.

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 and return format are front-loaded in the first two sentences, followed by a compact per-parameter list. Nothing is padded, though the parameter block reads as a flat enumeration rather than prioritized guidance.

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?

An output schema exists so return values need no explanation, and all five params are addressed. Defaults (max_results=100, empty path) are only partially surfaced in prose, leaving minor gaps for a 5-param search 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 description coverage is 0%, so the description must carry the load, and it documents all five parameters. It adds genuinely useful non-obvious semantics ('empty means the first root', glob matches relative path), though a couple entries (ignore_case) are near-tautological restatements.

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 (Search), resource (file contents), and mechanism (regular expression), and even specifies the return shape ('file:line: text'). 'File contents' cleanly distinguishes it from the sibling find_files (name-based) without needing to name 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?

Offers an implicit scoping hint ('Narrow it: ~/dev is large') and explains what each filter does, but never states when to reach for this tool versus find_files or read_file, nor any exclusions. Usage is implied rather than directed.

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 destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is covered. The description adds real context beyond that: the whole-file replacement semantics (existing content is destroyed, not merged) and the automatic creation of missing parent folders, which no annotation states.

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 short lines, zero waste, with the core action and the parent-folder side effect front-loaded before the parameter glosses. Every sentence 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?

An output schema exists, so return values need not be explained, and annotations cover the destructive/idempotent profile. What remains is minor: no path format guidance and no explicit pointer to edit_file, but the definition is sufficient to invoke 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?

Schema description coverage is 0%, so the description carries the burden for both parameters. "content: the complete new contents" usefully reinforces that the value must be the entire file rather than a patch, but "path: the file to write" is a near-tautology and no format, encoding, or relative-vs-absolute guidance is given.

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?

"Create a file or replace it whole" is a specific verb+resource with a clear scope qualifier that separates it from the sibling edit_file, which implies partial modification. It stops short of naming that sibling explicitly, so it is clear but not fully differentiated.

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 "replace it whole" hints at when this is appropriate (full-file rewrites vs. incremental edits), but there is no explicit when-to-use/when-not guidance and the sibling edit_file is never named. Usage must be inferred from the contrast.

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