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

With no annotations, the description carries the full burden and does substantial work: it discloses the @types/* fallback and the two distinct return shapes (declarations with JSDoc and file:line vs. version plus exported names). Still missing: read-only confirmation, error behavior when a package is not installed, and any size/truncation limits.

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 dense sentences, front-loaded with the core action, then branching cleanly on the optional symbol parameter. No filler text.

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 the description does describe both return shapes reasonably. It falls short on project_dir and on failure modes for a 3-parameter tool, but the essentials needed to call it are present.

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 0%, so the description must explain parameters. It defines the symbol parameter's effect well and implies that package refers to an installed package, but project_dir is completely unexplained and its purpose (monorepo root? alternate install dir?) is left to guesswork.

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: reading TypeScript declarations of a package installed in node_modules, with the @types fallback named. It is clearly different from py_* siblings and from node_versions, though it never names those siblings 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?

The with/without-symbol branches imply what each mode is for, but there is no explicit when-to-use or when-not-to-use guidance, and no routing to node_versions or py_inspect. The agent must infer the choice.

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; it usefully discloses two behavioral facts beyond the name: the search starts at the *nearest* node_modules (upward resolution) and results are rendered as name@version. It does not say what happens when no node_modules is found, whether matching is case-sensitive or regex, or how an absent pattern behaves.

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 zero waste, front-loading the verb and resource and packing output format and filter semantics in the same clause.

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 read tool with no annotations and no output schema, the description covers purpose, output format, and filter semantics reasonably. The unexplained project_dir and undefined empty-pattern/no-install behaviors leave meaningful gaps an agent would need to guess at.

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 0%, so the description must compensate. It does clarify that 'pattern' is a substring match on the package name, but 'project_dir' is left completely undefined — no hint whether it is a start directory, a path to a node_modules, or an absolute vs relative path.

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?

Clear verb ('List') plus resource ('packages installed in the nearest node_modules') and even the output shape ('name@version'). It implicitly distinguishes itself from the py_* siblings by naming node_modules, though it never explicitly contrasts with py_versions or node_types.

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?

No statement of when to use this versus py_versions/node_types, and no prerequisites or exclusions. The only usable signal is the implicit ecosystem cue from 'node_modules', leaving the agent to infer the rest.

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. It usefully discloses that inspection happens in the project's live interpreter and reports the defining file:line and installed distribution version, but it says nothing about import side effects, failure behavior for unresolvable targets, or the effect of max_members truncation on results.

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, zero filler, with the scope constraint and return contents front-loaded and the parameter format example trailing as supporting detail.

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?

No output schema exists, and the description does the required work by enumerating the returned fields (signature, docstring, members, file:line, distribution version). It falls short only on error/truncation behavior for a 4-parameter introspection 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 only 25% (only include_project is documented), so the description must compensate. It does add real value for `target` by giving dotted-path examples like 'requests.Session.request' and 'pandas.DataFrame.merge', but `max_members` (default 80, truncation semantics) and `project_dir` are left undocumented in both places.

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?

Specific verb (inspect) plus a precise scope: 'a Python object as installed in the project's own interpreter', with an explicit enumeration of what is retrieved (signature, docstring, members, file:line, distribution version). That enumeration implicitly separates it from py_source (source bodies) and py_versions (version listing), but 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?

The phrase 'as installed in the project's own interpreter' implies when to use it (runtime introspection of the actually-installed package rather than other environments or source files), but the description never states when not to use it or names py_source/py_versions as the alternative for source-reading or version-listing tasks.

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. It mentions truncation (max_chars) and that the target must be installed, but omits whether the operation is read-only (implied), what happens if the target is not found, and other behavioral traits like error handling or return format.

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 a single, front-loaded sentence with zero waste. It starts with the core action and includes the truncation note without unnecessary detail.

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?

Given no annotations, no output schema, and zero schema description coverage for four parameters, the description is far too sparse. It lacks usage guidance and fails to explain two of the four parameters, leaving significant gaps for an agent to invoke 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 0%, so the description must compensate. It only explains max_chars via '(truncated to max_chars)' and indirectly describes 'target' as an installed Python function/class/module, but leaves project_dir and include_project completely 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?

The description states a specific verb (Return) and resource (source code) with a clear scope (installed Python function/class/module). It does not explicitly differentiate from siblings like py_inspect, but an agent can infer the distinction without opening schemas.

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 guidance on when to use this tool versus alternatives such as py_inspect or py_versions. The description only states what it does, leaving the agent to infer usage context.

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 burden. It discloses the important behavioral scope (reads the project's interpreter, not the ambient environment) and the "name==version" output form, but says nothing about failure modes (missing interpreter), cost, or whether output is ordered/filtered further.

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 dense sentence: verb first, parenthetical output format, then the parameter caveat. Nothing wasted and no postamble.

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 2-param read-only listing tool with no output schema, the description covers the core behavior adequately, but leaves one of two parameters (project_dir) and the return shape (list of strings? structure?) undocumented.

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 compensate: it fully specifies `pattern` (substring match, empty means all). `project_dir` is only obliquely implied by "the project's interpreter" — its purpose, default, and accepted format are never stated.

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?

Specific verb ("List") plus a precise resource ("installed Python distributions") and scope ("in the project's interpreter"). The Python-specific framing clearly separates it from node_versions/node_types siblings, 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?

"empty pattern lists all" is useful call-time guidance for the optional pattern, but there is no when-to-use/when-not guidance and no reference to the sibling tools (py_inspect, py_source, node_versions) that an agent could confuse it with.

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