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 matching is exact and case-insensitive (not semantic/fuzzy) and that results are verbatim snippets with pointers, but says nothing about result limits, permissions, or what happens on no-match.

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 with little waste, but the lead phrase 'Where these exact words were asked' is grammatically awkward and front-loads a clause rather than the action or resource, forcing the reader to reconstruct the purpose.

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 3-param, one-required tool with no annotations and no output schema, the description covers matching semantics and return shape reasonably, but omits the meaning of 'limit' and any routing guidance relative to its siblings, leaving 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 description coverage is 0%, so the description must compensate. It does decode the 'in' enum values (asked/answered/attached) which is genuinely additive, but 'limit' is completely unexplained and 'phrase' is only obliquely referenced as 'these exact words'.

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 scopes the corpus (local sessions, canvases, Claude Code/Codex memories) and the operation (exact, case-insensitive matching), but never states a clear leading verb and never distinguishes itself from siblings like recall_turn or why_file. An agent gets the search domain but must infer that this is a literal full-text 'find' rather than a semantic lookup.

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 the sibling tools recall_turn, why_check, or why_file, and no stated prerequisites or exclusions. The Q/A/M breakdown hints at scope but is not framed as selection criteria.

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 discloses the return contents (question, answer, tool calls with diffs) and that session IDs can be prefixes, which is helpful. But it does not state that the operation is read-only, whether there are side effects, or what happens on invalid input, leaving key behavioral traits implicit.

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, densely packed sentence with zero wasted words. It front-loads the tool's output ('One turn in full') and then clarifies the parameters, making it easy to scan.

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 two-parameter retrieval tool with no output schema and no annotations, the description is fairly complete: it explains the return values and how to source the turn number. It omits edge-case behavior (e.g., missing session or turn) and does not state read-only status, but those are minor gaps given the tool's simplicity.

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 adds that 'session' can be a prefix and that 'turn' is a number obtained from why_file, which is useful. However, it does not explain the format of session (e.g., string pattern) or turn (e.g., integer range), so semantics remain partially specified.

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 resource ('One turn in full') and enumerates its contents (question, answer, tool calls with diffs), making the tool's function clear. It references the sibling 'why_file' for turn numbers, but does not explicitly contrast itself with 'find' or 'why_check', so sibling differentiation is only partial.

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: the turn number is 'as shown by why_file', suggesting a workflow where why_file is consulted first. However, there is no explicit when-to-use or when-not-to-use guidance, nor are alternatives like 'find' or 'why_check' 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?

No annotations are provided, so the description carries the full burden. It usefully discloses cost ("cheap"), output shape ("one line; history true/false"), and scope (local agent sessions), but says nothing about permissions, latency beyond cost, or what qualifies as "history," leaving meaningful behavioral gaps 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?

Two tight clauses, front-loading the usage trigger and then the cost/return profile. No filler sentences and nothing buried.

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 supplies the return format (one line, boolean) and the cost profile, which is sufficient for a trivial query tool. The only gap is not routing against the similar-sounding why_file sibling.

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% and the single path parameter is fully documented in the schema (file path, URL, or arxiv:<id>). The description adds no meaning beyond "this artifact," so the schema does the heavy lifting and baseline 3 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 states a specific verb+resource: it checks whether an artifact has history in local agent sessions, and clarifies the return is a one-line true/false. It is clear, but it never distinguishes itself from the sibling why_file, which sounds closely related, so an agent could still hesitate between 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?

"Cheap first question before editing a file" gives a concrete when-to-use trigger and implies a cost-based ordering of calls. It does not name alternatives (e.g., why_file) or state when-not to use it, so it stops short of full routing guidance.

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, and it does disclose useful semantics: the span of sources covered (local Claude Code, Codex, DeepSeek Harness, Pi, ThoughtDAG) and the epistemic caveat that '≈' is a candidate explanation, not a verified reason. It does not disclose read-only vs mutating behavior, auth requirements, result ordering, or volume/pagination 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?

A single dense clause with no filler; each element (when, Δ, asked, answer, deep link) earns its place. It is slightly awkward to parse because it is a fragment with symbolic notation (Δ, ≈) and no leading verb, which costs a bit of front-loading.

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 responsibly sketches the return contents (timing, change, prompt, candidate explanation, deep link). Missing for a 3-param tool with zero annotations are the mutation/safety profile and any hint about result volume or the meaning of the defaulted `limit`.

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 67%: limit and include_read are self-documented in the schema, while the required `path` has no description. The description partially compensates by revealing that the target can be a 'file, URL or paper', which is non-obvious from the parameter name `path`. That is real added meaning, but it does not cover the remaining ambiguity.

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 is a noun phrase describing the payload ('The turns ... that touched a file, URL or paper') rather than a verb-led statement of what the tool does. The intended action (find/list turns that touched an artifact, with explanation) is inferable but never stated outright, and there is no differentiation from siblings like recall_turn or why_check.

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 when-to-use guidance, no statement of prerequisites, and no mention of how this differs from find, recall_turn, or why_check. The agent must guess the routing among four siblings purely from their names.

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