PIL

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

With no annotations, the description carries the full behavioral burden, and it does disclose the return content well (summary, key_points, howto, links, folders, tags). However, it says nothing about permission requirements, behavior when post_id is unknown/invalid, or any rate limits, so key behavioral traits remain undisclosed.

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 resource and then lists return contents; every clause carries information. The parenthetical enumeration is dense but not wasteful.

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 annotations and no output schema, the description partly compensates by detailing what is returned, which is genuinely useful. It still omits how to obtain post_id and what happens on a missing/invalid post, which an agent needs for reliable 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 0% for the single required post_id parameter, and the description never mentions the parameter at all. It adds no meaning about where post_id comes from (e.g., from search_posts or list results) or its expected format, so the parameter is 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?

States a specific verb ('Return') and resource ('one post') and enumerates the content categories returned (metadata, deep-read knowledge, folders, tags). It implicitly distinguishes itself from sibling search_posts by scoping to a single post, though it never names the sibling 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: call this when you have a post_id and need the full record for that post. There is no explicit when-to-use/when-not guidance and no mention of alternatives such as search_posts for discovery, leaving the routing decision 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?

No annotations are provided, so the description carries the full behavioral burden. It doesn't state whether the result is a computed aggregate, whether it is cached, what 'deep-read coverage' implies, or anything about permissions or cost beyond the bare summary phrase.

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, which is appropriately sized for a zero-parameter tool. However, 'deep-read coverage per field' is jargon that only becomes meaningful with more context that the description doesn't provide.

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 parameterless stats tool with no annotations and no output schema, the description needs to explain what the returned totals represent and how 'coverage per field' is computed. It doesn't, leaving the agent unable to interpret or trust the output.

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 is nothing for the description to disambiguate. Baseline 4 is appropriate — no parameter guidance is needed, and the description doesn't need to explain any inputs.

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 phrase 'Totals for the library plus deep-read coverage per field' is vague about what resources are counted and what 'deep-read coverage per field' means. It gestures at an aggregate/stats operation but doesn't clarify the domain (posts? tags? folders?) versus siblings like search_posts or list_tags.

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 indication of when to use this tool versus the sibling list/search tools. An agent cannot tell whether this is a summary view, a health check, or a prerequisite for other calls.

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. 'List' implies a read-only operation, and the item_count vs mapped_posts caveat usefully discloses a data-quality gap, but ordering, pagination, and auth requirements are unstated.

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 and resource, then the field caveat. Nothing is wasted.

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, so the description's explanation of item_count and mapped_posts does real work. It stops short of describing the folder identifier/name fields or whether results are paginated, which for a list tool without an output schema would have been worth one more clause.

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 for the description to disambiguate, and it correctly avoids inventing parameter guidance.

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 (list saved-post collections) and clarifies the domain term 'rooms'. The resource is clearly distinct from siblings like list_tags or get_post, 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 only implied by the verb 'List' — an agent can infer this is the browse-collections entry point, but there is no statement of when to prefer it over library_stats or search_posts, and no prerequisites or exclusions are given.

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 discloses the sort order, which is useful, but says nothing about pagination, result cap behavior, auth requirements, or result shape. One behavioral fact is not enough for an unannotated tool.

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 clause, front-loaded with the verb and resource, with the ordering constraint attached. Nothing wasted.

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 read-only list tool with no output schema, the core purpose and sort order are covered, but the sole parameter's meaning and any result-size behavior are absent, leaving a real gap for an agent sizing its request.

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?

One parameter (limit, default 100) with 0% schema description coverage, and the description never mentions it. The agent gets no indication of what limit governs or what happens at the boundary.

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 tags') and adds a meaningful ordering scope ('most-used first'). It doesn't name or differentiate from any sibling, but the purpose is immediately clear.

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 when-to-use, when-not, or alternative guidance. The ordering hint implies a discovery/browsing scenario, but nothing tells the agent how this relates to siblings like search_posts or library_stats.

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 burden and does disclose meaningful behavior: the match fields (captions plus summaries/key points/how-to), the return shape (compact cards with a has_knowledge flag), and the limit bound (1-50). It omits read-only/safety framing and any behavior for empty or no-match results, keeping it short of a 5.

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 sentences, front-loaded with the action before the filters and return shape; nothing is padded. Very little could be cut without losing parameter meaning, though the parenthetical listing of knowledge types is slightly verbose.

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 properly covers the return format (compact cards, has_knowledge flag) and the searchable surface. It is adequate for an agent to call correctly, with only edge-case behavior (no results, multiple tags) unaddressed.

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 and largely does: query is defined by what it matches against, folder accepts 'collection id or folder name', tag is singular ('one tag'), and limit is bounded at 1-50. Only minor gaps remain, such as tag matching semantics or default limit behavior.

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) and resource (the library) and clarifies what is matched (captions and deep-read knowledge), which distinguishes it from get_post and the list_* siblings. It does not name those siblings explicitly, so the differentiation is inferred rather than stated.

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 word 'Optionally restrict to one folder' and/or one tag' implies the usage pattern (broad search, then narrow), but there is no explicit when-to-use statement, no when-not, and no named alternative such as get_post for known IDs.

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