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

With no annotations, the description carries the full burden and does real work: it discloses the authorization precondition (owner-confirm token bound to the proposal hash), the pre-merge snapshot being persisted, and the path back via unmerge. It omits failure behavior (invalid/expired token, already-executed proposal) and idempotency, which matter for an irreversible-looking mutation.

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, then the precondition, then the scope restriction and reversibility note. No filler; every sentence adds a constraint the agent needs.

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 two-parameter mutation with no annotations or output schema, the description covers authorization, scope, and recovery (unmerge snapshot) adequately. It leaves the post-call outcome unspecified — whether a result record is returned and how to interpret success versus a hash mismatch.

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 0%, so the description must compensate, and it does for confirm_token by giving the exact format confirm-merge-<proposal_id>-<hash12>, which also clarifies the linkage between the two parameters. proposal_id itself is only implied (the proposal being executed) and no format is given.

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 ("Execute a proposed graph merge") and immediately bounds the scope with "Graph nodes only — never merges records inside a platform." That exclusion cleanly separates it from record-level siblings like record_ingest and from merge_propose/merge_unmerge.

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?

Implies the correct workflow via the required owner-confirm token "bound to the proposal hash," making clear this must follow a merge_propose step, and gives an explicit exclusion (platform records). It does not spell out what to do if the proposal is stale or the token mismatches, so it stops short of full when/when-not 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 burden and does disclose the crucial behavioral traits: it is non-executing, it yields evidence (matching keys by hash, conflicts) plus a proposal hash. It omits persistence/idempotency of the proposal, permission requirements, and what happens when the two records are not same-kind.

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, front-loaded sentences with zero filler; the leading PROPOSE and the closing doctrine note both earn their 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?

No output schema exists and the description does describe the return payload (evidence + proposal hash), which is a real strength. But for an unannotated write-adjacent tool with 0% schema coverage, leaving proposal_id and conflict-handling behavior unexplained leaves it only minimally viable.

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 0%, so the description must explain all three parameters. It implies record_a/record_b are two same-kind records and describes the returned proposal hash, but the proposal_id input parameter is never mentioned and must be inferred from context.

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 (PROPOSE) and resource (identity merge between two same-kind records), and the capitalized PROPOSE plus 'Executes nothing' separates it from merge_execute in the sibling list without needing 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 description makes the propose-before-execute workflow clear by emphasizing it executes nothing and returns a proposal hash, which implies handoff to merge_execute. It never names merge_execute or merge_unmerge explicitly, so the routing is inferred rather than 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?

No annotations, so the description carries full behavioral burden. It discloses the token-gated auth flow and the destructive scope ('restoring the pre-merge nodes exactly'), which is real added context, but says nothing about reversibility of the undo itself, permissions/ownership requirements, or what happens if the merge_id is invalid or already unmerged.

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 short sentences, zero filler, with the outcome stated first and the prerequisite second. 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?

For a 2-parameter mutation tool with no annotations and no output schema, the description covers purpose and the token prerequisite but leaves failure modes, idempotency, and return behavior unaddressed. Adequate to call it, not complete enough to call it confidently.

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 0%, so description compensation matters. It documents the confirm_token format precisely via 'confirm-unmerge-<merge_id>', which is genuinely useful, but merge_id is left unexplained (presumably a receipt/merge identifier) and neither parameter notes format, source, or constraints.

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: 'Undo a confirmed merge from its receipt snapshot, restoring the pre-merge nodes exactly.' That clearly separates it from merge_propose and merge_execute, though it never names a sibling explicitly, so the differentiation is implicit from the context of the merge family.

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 prerequisite 'Requires confirm-unmerge-<merge_id>' tells the agent this is the post-merge reversal path and that a token must first be obtained. It gives clear context for when to invoke, but no explicit when-not-to-use guidance (e.g. what to do if the merge is not yet confirmed or already unmerged).

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. 'Show' signals a read operation and the enumerated fields partly substitute for a missing output schema, but nothing is said about who may call it (policy data is often privileged), whether results are scoped to the caller's environment, or whether values are computed 'effective' tiers vs raw config.

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 sentence with the scope front-loaded and zero filler; every listed item corresponds to a category of information the caller receives.

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 zero-parameter, no-output-schema read tool the enumerated field list does real work in describing the return payload. What is missing is authorization/scope context — whether admin rights are required and whose policy is being shown — which matters materially for a policy tool.

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 no schema semantics to compensate for; baseline 4 applies. The description adds no parameter guidance because none is needed.

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 'Show' paired with a concrete enumeration of the returned policy artifacts (tier floors, effective tiers, kill switches, masking rules). An agent immediately knows this is a read-only policy introspection tool, and it is obviously distinct from the record/merge/reply siblings, 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?

The phrase 'in force' implies reading current/live configuration rather than historical or proposed policy, which is useful implied context. However, there is no explicit statement of when to call this versus other tools, no prerequisites, and no exclusions — usage must be inferred from the one-liner.

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 useful traits: the append-only/hash-chained nature, that verification occurs during the call, and that returned data excludes content. It omits what a failed verification looks like, whether it errors or reports, and 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?

Two short sentences, zero filler, with the core action and the key data-shape caveat front-loaded. Nothing could be cut without losing 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?

For a one-optional-param read tool with no output schema, the description covers return data shape well, but leaves the verification outcome semantics and the meaning of 'limit' unexplained. Adequate, not complete.

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 parameter 'limit' has 0% schema description coverage and is never mentioned in the description — no default, maximum, or meaning (page size vs. record cap). The description adds nothing beyond the bare schema property name.

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 the ... receipts') and adds defining properties (append-only, hash-chained, verification). The clause 'IDs + hashes only — never content' implicitly separates it from record_read/record_search, though no sibling is named outright.

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 explicit when-to-use guidance, no exclusions, and no named alternative among record_read, record_search, or policy_show. An agent can infer auditing/verification intent, but nothing tells it when this is preferable to the record_* tools.

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 and does disclose important ingest safeguards: required provenance, required ledger, untrusted tagging, and quarantine of instruction-shaped content. However, it omits core mutation behavior such as whether records are created/updated, idempotency, permissions, failure modes, and response 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?

Three dense sentences, front-loaded with the action and followed by the non-obvious constraints; there is no filler. The final security sentence adds specific, useful information rather than restating the name.

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 six-parameter nested ingest tool with no annotations and no output schema, the description covers governance requirements but not enough operational detail. An agent still lacks parameter-level guidance, return behavior, and error/idempotency 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 0% for six parameters, and the description only partially compensates by implying kind values and the need for field_provenance/data_rights. It leaves fields, record_id, external_ids, and nested object structures unexplained.

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 ('Ingest') and resource ('canonical Customer Graph record') and enumerates record kinds, so an agent knows the action and target. It does not explicitly name or distinguish siblings such as record_read/record_search, but the ingest verb makes the distinction largely 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?

It gives implied usage and prerequisites: records must carry provenance and include a Data Rights Ledger block. It does not state when to choose this over sibling tools or when not to use it, nor does it explain update-vs-create conditions.

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, and it does unusually well: it enumerates exactly which fields are masked per surface (owner full email, analytic domain-only, phone always partial, gov/payment/health null) and notes the call is 'Receipted', so the agent knows an audit trail is produced. It omits error behavior (missing record, unauthorized surface) and whether the read is side-effect free beyond the receipt.

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?

Masking rules are front-loaded in a single dense parenthetical and 'Receipted.' closes with a meaningful behavioral footnote. Every clause earns its place, though the parenthetical is heavy enough that a structured list would scan faster.

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 two-parameter read with no annotations and no output schema, the masking and receipt notes cover the most important surprise (redacted fields), but the description says nothing about the shape of the returned record or about failure modes. Adequate to call correctly, not complete enough to predict the response.

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 0%, so the description must compensate, and it partially does by defining what 'surface' means via the owner/analytic examples and their masking consequences. It never states the allowed surface values as an enumeration nor confirms that record_id is the canonical graph record identifier, so one parameter remains essentially 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?

A specific verb ('Read') and resource ('one graph record') with a stated scope of applying egress masking, which separates it from record_search (multi-record lookup) and record_ingest. It stops short of naming a sibling to route away from, so it is clear but not sibling-differentiating in the strongest sense.

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 phrase 'Read one graph record' implies retrieval by ID, and the exposure of a 'surface' parameter signals that callers choose an egress context, but there is no explicit when-to-use guidance, no statement of when to prefer record_search, and no prerequisites. Usage is inferable rather than 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?

No annotations exist, so the description carries the full burden. It does disclose two non-obvious behaviors: results are masked, and the query is logged as a receipt by hash only, which is meaningful side-effect context. It omits read-only status, result limits, pagination, and permission requirements, leaving significant gaps for a tool with zero annotation coverage.

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 short sentences with the core mechanic front-loaded and no filler. The second sentence about receipting is unusual but earns its place by disclosing a privacy-relevant side effect.

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, no output schema, and three undocumented parameters, the description is too thin. It never explains what 'masked' means for usability, what 'surface' controls, or how many results come back, all of which an agent needs before calling it.

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 0% for all three parameters. The description implicitly covers 'kind' (record kind filter) and 'query' (substring), but says nothing about their optionality, matching semantics, or case sensitivity, and 'surface' is never mentioned at all.

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 ('Search graph records') plus the matching mechanism ('by kind + substring') and the shape of the return ('masked summaries'). That is enough to separate it from record_read or record_ingest, 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?

The kind+substring matching implies the discovery use case, so an agent can infer this is the lookup tool rather than the by-ID fetch. However, there is no explicit when-to-use, no exclusions, and no pointer to record_read or receipt_list as alternatives.

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 and does unusually well: it discloses grounding rules, citation-list output, MISSING_FACT markers for untraceable facts, that customer text is never a fact source, and that instruction-shaped messages are quarantined and reported rather than obeyed. It still omits whether the draft is persisted (a write side effect), whether it requires prior ingestion, and any permission or failure 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?

Three tight sentences, front-loaded with the purpose and followed by the behavioral guarantees. No filler and 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?

Behaviorally rich for a tool with no annotations and no output schema, and the citation/MISSING_FACT contract substitutes well for a return-value spec. However, for a 3-parameter tool with 0% schema coverage it leaves the parameters and any persistence side effect unexplained, which is a real gap 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% across three parameters, so the description must compensate and does not. 'ticket reply' weakly implies ticket_id, but draft_id (is it an existing draft to fill, or new?) and person_id (author? recipient?) are left entirely undefined, and required-vs-optional meaning is absent.

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 ('Draft a ticket reply') plus its core constraint ('ONLY from record facts, with a citation list'). It is clearly distinguishable from siblings like record_read/merge_execute by domain, though it never explicitly contrasts with 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?

There is no when-to-use guidance: no prerequisites (must records be ingested first?), no statement of when to prefer this over manually composing or over any sibling, and no exclusions. 'ONLY from record facts' is a constraint on output content, not routing guidance.

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