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

With readOnlyHint/openWorldHint already covering safety, the description still adds substantial behavioral context: no retry, no body validation, no status-checking, no redirect following unless asked, and the counterintuitive ok:true-with-500 semantics. This is exactly the kind of non-obvious contract an agent needs.

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?

Three sentences, front-loaded with the core action and return payload, then the non-judgment semantics. Slight redundancy in the negative list ('does not check the status', 'does not validate', 'does not retry') but every clause carries distinct meaning.

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 an output schema present, the description needn't explain return values, and it still describes the observation envelope (ok flag, http_status, observed time, IP). Combined with a fully documented 8-parameter schema, nothing needed to invoke it correctly is missing.

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%, so the schema already documents every parameter including body serialization, redaction, truncation, and redirect revalidation. The description only echoes follow-redirect behavior and adds no syntax or format detail 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?

Names a concrete verb and resource ('Make one HTTP request') and enumerates exactly what is returned (status, headers, body, observation time, connected IP). The phrase 'Measures from the server's network position' cleanly separates it from the sibling facts.measure.ws and from any client-side fetch.

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 'does NOT judge the result' paragraph effectively defines the boundary against an assertion tool (facts.recall.assert): this tool observes, it does not evaluate an expectation. No sibling is named explicitly and no exclusion is given for facts.measure.ws, so it falls short of a 5.

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 only cover readOnlyHint/openWorldHint; the description adds substantive behavior beyond that: measurement origin (server's network position), the fact that zero messages is a valid observation rather than a failure, and that silence is not diagnosed. It does not cover auth/network-policy expectations or the truncation semantics handled elsewhere, and the readOnlyHint sits slightly uneasily with the optional `send` capability.

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?

Purpose is front-loaded in the first sentence, followed by a one-line measurement-scope note and a compact negative list. The trailing clause 'does not say whether silence is a problem' is mildly redundant with the preceding zero-messages statement, but otherwise every clause carries information.

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 nine parameters, nested `send` objects, and an output schema, the description supplies the behavioral framing the schema cannot (timing origin, silence semantics, no reconnection). It is nearly complete, lacking only mention of the network policy / authorization context that the schema references for `url` and `headers`.

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%, so every parameter (listen_seconds, max_messages, max_message_bytes, headers, send, etc.) is already documented in the schema, including caps and defaults. The description adds only timing semantics ('offset from the open'), so the baseline 3 for schema-driven coverage is correct.

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 precise verb chain (connect, listen for N seconds, return arrived messages with absolute time and offset from open) and names the resource (WebSocket), which cleanly separates it from the sibling facts.measure.http. An agent knows exactly what this tool produces without reading 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?

It gives explicit negative scope -- does not wait for a particular message, does not interpret payloads, does not reconnect -- which tells the agent when this observation tool is the wrong choice for waiting/asserting on a specific message. However, it never names the alternative tool (e.g. facts.recall.assert) that would be correct for that job, so routing is left 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?

Annotations declare a non-read-only, non-destructive, closed-world write, and the description goes beyond them: it discloses that only evidence existence and project ownership are validated, that semantic support is deliberately NOT checked, and that evidence is embedded for auditability. It omits idempotency/duplicate handling and error behavior for a mutation tool, which keeps it from 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?

Three sentences, front-loaded with the action and payload, then the scoping negations and the auditability rationale. Every sentence earns its place, though the 'that would be interpreting' aside and the final clause slightly pad an otherwise tight definition.

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 an output schema available, return values need no explanation, and the description covers the write semantics and validation boundary well for a 6-parameter mutation. Remaining gaps are minor: no statement on duplicate/conflicting claims or on what happens if the referenced evidence is missing.

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%, so the schema already documents every parameter including the observed_at derivation rule and the evidence union. The description restates the field set without adding format, syntax, or constraints beyond what the schema provides, which is the expected baseline here.

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 ('Write a claim into the project registry') and enumerates the payload fields. The explicit negations ('does NOT measure anything') separate it from the facts.measure.* siblings, so an agent can distinguish it without opening other 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?

The description draws a clear boundary: use this to record a claim, not to measure and not to interpret evidence. It does not name any alternative tool (e.g. facts.recall.query for reading) or state prerequisites, but the when-not conditions are explicit enough to route correctly.

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 cover the safety profile (readOnlyHint=true, idempotentHint=true, openWorldHint=false), so the bar is lower. The description still adds real behavioral context beyond them: the events are returned raw, ordered, unrewritten, and shaped as 'an assert, then a retract if there was one.' That is genuinely useful for interpreting the log.

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 core action and scope. Every clause earns its place and none of it repeats structured fields.

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 an output schema present, return values need not be described, and annotations carry the safety profile. The description adds the audit framing and event shape, leaving only the relationship to sibling recall tools unspecified — a minor gap for a simple two-parameter read.

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%, so the schema already documents both parameters ('project whose registry to read', 'claim whose events to return'). The description adds no further syntax or semantics beyond what the schema provides, which is the correct baseline when the schema does the heavy lifting.

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 ('Return the raw events of one claim, in order') with the scoping qualifier 'exactly as they sit in the log.' This implicitly separates it from facts.recall.query (current state) and facts.recall.assert/retract (mutations), but it never names a sibling, so the differentiation is inferential rather than explicit.

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 via the audit framing ('auditable proof that nothing was rewritten'), which suggests a forensic/verification context. It never states when to prefer this over facts.recall.query or when it is unnecessary, so the agent must infer the boundary itself.

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, idempotentHint and openWorldHint=false, so the safety profile is covered; the description nonetheless adds real value by confirming no socket activity and disclosing output traits — per-claim age and stale mark, a remeasure_with field, and retraction visibility semantics. It does not discuss permissions, limits beyond paging, or failure behavior, 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?

Front-loaded with the core action, then the non-measurement guarantee, then return and retraction behavior — a sensible order. Three sentences with little waste, though the read-only point is restated in two guises ("NEVER measures" / "returns what was recorded"), which slightly dilutes it.

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 13 fully documented parameters and an output schema present, the description only needs to supply the behavioral frame, and it does: read-only, closed-world, snapshot-consistent paging, and non-destructive retraction. Nothing an agent needs to invoke this correctly is missing.

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 each of the 13 parameters has a detailed inline description, so the schema does the heavy lifting and a 3 is the correct baseline. The prose only adds conceptual color about retracted claims, not syntax or semantics 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 ("Read claims from the project registry") and immediately delimits scope against the measure siblings: "It NEVER measures and opens no sockets: it returns what was recorded." An agent can distinguish this from facts.measure.http/ws and the other recall tools without opening a 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?

Gives clear context for use — read recorded claims rather than produce fresh measurements — and covers a key behavioral branch ("Retracted claims are hidden unless asked for"). It never explicitly names an alternative tool or the condition that selects facts.recall.history/assert/retract, so routing is implied rather than spelled out.

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 declare destructiveHint=false, and the description goes further with concrete append-only semantics: the original line stays byte for byte, the retraction is a new event, and no parameter removes anything. That is exactly the kind of behavioral context annotations cannot express on their own.

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?

Three short sentences, front-loaded with the action, then the immutability guarantee. No filler and every sentence carries distinct information.

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?

A mutation tool with annotations and an output schema needs little more, and the immutability disclosure closes the biggest risk of misinterpretation. The remaining gap is the superseded_by parameter's role in distinguishing supersession from retraction, which is left entirely to the 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 description coverage is 100%, so the schema already documents all five parameters including the required reason and by. The description restates that a reason and author are attached but adds no syntax or semantics for superseded_by (e.g. that it must exist in the same project), so 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?

Specific verb+resource ('Mark a claim as retracted') with the required evidence named (reason, author). It distinguishes itself from a hypothetical delete tool, but never contrasts with actual siblings like facts.recall.assert or facts.recall.history, which the agent must choose between.

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 'Mark a claim as retracted' and the note that there is no delete tool, so the agent knows this is the only removal-adjacent path. However, it never says when to retract versus supersede, nor when to use the optional superseded_by versus a plain retraction.

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