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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds real value beyond that by enumerating what comes back: full text, OCR of image text, quoted post, full X Article text, and contained links — an agent knows the payload is enriched, not raw.

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 front-loaded sentence with the action and keying method first, followed by an enumeration of return content. Dense but every clause (images, quotes, article text, links) conveys distinct payload information; 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 correctly shouldered the return-value burden and did so thoroughly. However, it leaves gaps around failure behavior (invalid id, non-saved post), and doesn't clarify whether 'saved post' restricts the lookup to the user's library versus any public post.

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 single schema parameter 'post' has 0% description coverage, so the description must compensate — and it does, specifying that it accepts either a post id or an x.com/twitter.com URL. That accepted-format detail is the key semantic an agent needs and is absent from the 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 retrieval action (fetch one saved post in full) on a specific resource, scoped to 'saved post' and passable by id or URL. The 'one ... in full' framing implicitly distinguishes it from the sibling list/search tools (search_saves, recent_saves), though it never names them.

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: use when you already hold a post id or x.com/twitter.com URL and want that single post. There is no explicit statement of when to prefer this over search_saves or recent_saves, and no guidance on what happens if the post isn't in the saved library.

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 and closed-world, so the safety profile is covered. The description adds genuine value by disclosing the payload composition (counts, date range, top people, top topics), which substitutes for the missing output schema; it does not mention cost or whether it scans the entire library.

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 sentences, zero filler, with the content of the summary front-loaded and the usage hint placed last. Every clause 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?

With no parameters, no output schema and full annotation coverage, the description carries the remaining burden and does so by enumerating the returned fields. Minor gaps remain around how many top people/topics are returned and any latency implications of aggregating a full library.

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 and the schema is trivially complete, so the baseline of 4 applies. No parameter meaning needs to be conveyed in prose.

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 specific resource (the user's saved X library) and enumerates exactly what the summary contains: bookmark/like counts, date range, top saved people, and common topics. This is clearly distinct from the sibling tools search_saves, recent_saves and get_post, which return individual posts rather than aggregates.

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?

"Useful before answering broad questions" gives a clear usage context and implicitly routes narrow lookups to the search/get siblings. It stops short of explicitly naming those alternatives or stating when not to use it (e.g. for a single post or a specific saved item).

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, so the safety profile is covered. The description adds real behavioral context beyond that: result ordering, the hard cap of 50, allowed filter dimensions, and accepted date formats — enough for an agent to predict output shape without trial calls.

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 identifying the resource first, then the optional filters, then the cap. No filler, and the dense parenthetical is a compact enumeration rather than prose padding.

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 read-only list tool with no output schema, the description covers ordering, scoping, filters, and limits adequately. The remaining gap is sibling disambiguation (search_saves) and the meaning of the source enum values, which matter 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 0%, so the description carries the burden, and it does most of it: it enumerates the has values, explains since/until as YYYY, YYYY-MM or YYYY-MM-DD, and states the limit ceiling. It does not explain what source='both'/'bookmark'/'like' mean or note the default limit of 15, both of which remain undocumented.

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 resource (the user's recently saved X posts) with ordering (newest first) and an explicit cap (Max 50), so the agent knows exactly what it returns. It does not, however, distinguish this from the sibling search_saves, leaving the agent to infer the boundary between 'recent' and 'search'.

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: the tool is for browsing recent saves with optional narrowing filters. The description never says when to prefer it over search_saves or get_post, nor any exclusions, so the agent must guess the selection rule.

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, and closed-world, so safety is covered. The description adds real behavioral value beyond that: results are ranked best-first, capped at limit (max 25), and dates refer to publication time of the post. It stops short of permission/auth requirements or coverage caveats.

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, then operators, then result semantics — logical ordering with little waste. The operator list is dense but every item documents a real capability, so it earns its space.

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 read-only search with no output schema, the description covers intent, input operators, and a basic notion of output (up to 25 ranked posts). The main omission is explicit linkage between the in-query operators and the seven structured parameters, which the schema alone makes ambiguous.

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?

Despite 0% schema description coverage, the description documents that queries accept X-style operators (from:, is:bookmark/is:like, has:image/video/link/article, year:/since:/until:) whose value sets line up with the has, source, author, since, and until parameters, plus the limit ceiling. The gap is that it never states these can also be supplied as separate structured parameters, leaving the agent to infer the mapping.

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 user's saved X posts / bookmarks and likes), plus scope details like semantic search, OCR on images, and full Articles. This clearly distinguishes it from recent_saves, get_post, and library_overview without requiring the 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?

The example ("that thread about pricing") tells the agent this is a natural-language recall tool rather than a structured query, which is useful context. However, it never explicitly routes to siblings — e.g., when to use recent_saves instead, or get_post to open a specific result — so the when-not guidance is missing.

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