ChatAtlas-local

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

Annotations already declare readOnlyHint, idempotentHint and non-destructive, so the safety profile is covered. The description adds useful scope context (it reports counts, date coverage, tags, and import recency), but does not say whether these are cached snapshot values or freshly computed, or roughly how large the response is. That is reasonable but not rich added disclosure.

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 compact sentence that front-loads the core answer ('what the archive holds') and then lists the specific fields. No filler, no repetition of the tool name or title; only minor gain from splitting the enumeration into a readable list.

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, so the description must carry the return-value burden, and it does by naming the four things returned. For a zero-parameter, read-only summary tool that is essentially complete; only the lack of guidance on when to call it leaves a small 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?

The tool takes zero parameters, so the baseline is 4. The description correctly makes clear there is nothing to filter or configure - it is a whole-archive summary - which matches 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?

The description gives a specific verb-plus-resource ('what the archive holds') and enumerates the exact contents: per-platform chat counts, covered date ranges, tags in use, and last import date. That enumeration separates it from chat-level siblings like list_chats and read_chat, though it never names them 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: the contents described suggest it is an orientation/first-call tool, but the description never says 'call this before searching' or when to prefer it over search_chats or list_chats. No exclusions or prerequisites are 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 readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description contributes the result ordering ('newest first') and the line-level shape with ids, but says nothing about pagination behavior beyond the schema, total counts, or result 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 tight sentences, zero filler, with scope and ordering front-loaded ahead of the read_chat pointer. Nothing is redundant or padded.

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's note that each line carries a chat id partially covers the return shape, and filters are fully covered by the schema. What remains thin is the distinction from search_chats and pagination expectations.

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%, with each filter (tag, title, since, until, platform, limit, offset) documented in-schema, so the baseline is 3. The description restates the filterable dimensions without adding syntax or defaults beyond 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 verb and resource ('Browse the user's saved conversations') plus ordering and filter dimensions, so the agent knows exactly what it returns. It does not differentiate itself from the sibling search_chats, leaving the list-vs-search boundary implicit.

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 'newest first' and the closing hint that each line carries the id for read_chat, which sketches a browse-then-read workflow. However, there is no explicit when-to-use-this-instead-of-search_chats guidance or stated preconditions, so 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?

Annotations already declare the safe, read-only, idempotent profile. The description adds valuable behavior beyond annotations: messages are numbered from 1, long chats are paged via from_message, and oversized messages are split into parts via part.

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 three compact sentences, front-loaded with the main action and then the pagination behavior. 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?

For a simple read tool with full schema coverage and annotations covering safety, the description is largely complete. It explains paging and message-part handling, though it leaves return-shape details implicit since there is no output schema.

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%, so the baseline is 3, but the description adds conceptual meaning by explaining how from_message and part are used to continue reading across pages and message parts.

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 and resource: reading one saved conversation message by message. The phrase 'one saved conversation' clearly distinguishes it from the sibling search/list tools that handle collections.

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 explains continuation behavior for long chats and long messages, which is useful usage guidance. However, it does not explicitly say when to choose this tool over search_chats, list_chats, or archive_overview.

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 needs no restatement. The description adds value by disclosing the shape of the returned data (counts, tags, titles per week), which matters because no output schema exists, but it says nothing about how aggregation is scoped or whether results are paginated.

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 with a colon list of returned elements; no filler. The trailing clause 'the chats' titles week by week' is slightly awkward but still informative.

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 burden of describing returns and does so concretely for a two-optional-parameter read tool. Minor gaps remain around aggregation scope (all platforms combined vs. per-platform totals) and result size.

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% – both 'days' (default 30, max 3650) and 'platform' (enumerated examples) are documented in the schema. The description only echoes them loosely ('over a stretch of days', 'each platform') without adding format or default details, so the baseline 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 names the resource (topics the user discussed with their AIs over a date range) and enumerates the specific aggregates returned: per-platform chat counts, top tags, and titles by week. That is specific enough for an agent to tell it apart from list_chats or read_chat, though it never names a sibling or a verb.

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 choose this over search_chats or list_chats, no mention of prerequisites, and no exclusions. The agent must infer that this is a summarization/analytics view rather than a retrieval tool.

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 safety is covered. The description adds real behavioral detail beyond that: AND-semantics across query words, prefix and accent normalization, result ordering (title matches first, then newest), and that the best-matching message is quoted in 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?

Dense but front-loaded: the search action, then the matching rules, then ordering, then the result shape. Every clause carries information, though the single run-on sentence packs the ordering and return details together in a way that is slightly hard to parse.

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 compensates by describing the return contents (chat id, quoted best-matching message) and ordering. For a 6-parameter search tool that is nearly complete; only ordering stability across large result sets and the effect of the filter parameters on ranking go 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 coverage is 100%, so the baseline is 3; the description earns above baseline by explaining the matching semantics of the required 'query' parameter (word-splitting, prefix expansion, accent handling) that the schema's one-line 'The words to look for' does not convey. The optional tag/since/until/platform/limit filters are left entirely to 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 verb and resource ('Find the user's saved conversations') and goes further to define what a match means: every query word present in title or messages, prefix matching, accent-insensitive. This clearly separates it from list_chats (enumeration) and read_chat (fetch by id).

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 trigger condition is clear — use this when looking for chats that 'mention something' by keyword — and the description routes the follow-up step to read_chat via the returned id. It never explicitly contrasts itself with list_chats (browse) or recent_topics, so the sibling differentiation is implied rather than stated.

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