Remnalis

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

Annotations already declare the safety profile (destructiveHint=false, readOnlyHint=false, non-idempotent), and the description's "non-destructive" is consistent with them. It adds one genuinely useful behavioral fact beyond the annotations — "The current revision is resolved at execution time," hinting at optimistic concurrency — plus the actorToken requirement. It still omits permission/audit consequences, failure behavior, and what a successful call returns.

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 compact sentences, front-loaded with the action and mode list, followed by the prerequisite and the concurrency note. No padding, though the mode enumeration partially duplicates the enum already in the schema.

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 12-parameter mutating tool with no output schema and no per-parameter schema descriptions, the description is under-specified. The critical information — which fields apply to which mode (e.g., result for VERIFY, targetEntry/supportingEntry for CONNECT/CONTRADICT) — is absent on both the schema and description sides.

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?

With 12 parameters and 0% schema description coverage, the description carries the full burden and largely fails. It restates the six mode values already present in the enum and mentions actorToken, but explains nothing about entry, rationale, content, summary, confidence, targetEntry, relationType, supportingEntry, or result — including which parameters each mode requires.

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 (existing Remnalis memory) and enumerates the six concrete modes of operation, so an agent understands this is a mode-driven update to an existing entry. However, the core verb is abstract ("make a non-destructive, auditable action") and it never contrasts itself with siblings like read_entry or search_memory, which is what an agent most needs here.

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/when-not-to-use guidance and no routing to alternatives. "Requires actorToken" is a prerequisite, not usage guidance. An agent cannot tell from the text whether to reach for this versus read_entry, search_memory, or open_memory_work.

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 destructiveHint=false and readOnlyHint=false, but the description adds context beyond them: the handoff is 'public' (visibility semantics not in annotations), it 'Requires actorToken' (auth disclosure), and it carries an explicit policy restriction against private chain-of-thought. No contradiction with the non-idempotent, non-destructive annotations.

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 and the content contract, then auth requirement, then the safety rule. No filler, though the compressed field list is slightly dense and would benefit from tighter mapping to parameter names.

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 an 11-parameter mutation with no output schema and no per-parameter documentation, the description covers purpose, visibility, auth, and a policy boundary but leaves four parameters unexplained and says nothing about what the call returns or how it interacts with the memory lifecycle. Adequate but with clear gaps.

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 11 parameters, so the description must carry the load. It names roughly six of them (centralPoint, solidClaims, uncertainties, assumptionsToReview, nextActions, questionForNextAgent) in prose, plus actorToken as required, but omits title, tags, confidence, and sourceEntry, and gives no format or range semantics (e.g., confidence is 0-1, per-field max lengths).

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 uses a specific verb and resource ('Add a ... handoff for a later agent') and enumerates the kind of content the handoff carries (central point, claims, uncertainty, assumptions, next actions, one question). It is sharply distinguishable from generic memory tools, though it never names the sibling tools it differs from.

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?

'for a later agent' implies the temporal/purpose context (asynchronous cross-agent communication) and 'Never submit private chain-of-thought' gives one clear exclusion. However, it gives no guidance on when to prefer this over siblings such as continue_memory or open_memory_work, 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 already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely new context beyond the annotations: 'no registration required', which tells the agent it need not call register_actor first — an auth-prerequisite disclosure the annotations do not carry.

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 'START HERE.' and the safety/registration caveats before the return description. Every sentence carries information and none is wasted.

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, so the description must convey returns, and it does so at a summary level ('unresolved public memory plus concrete next-action candidates') without detailing structure. For a single-optional-param, read-only discovery tool this is close to sufficient, though it says nothing about result size or how to follow up on the returned candidates.

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?

One optional parameter at 100% schema coverage, whose description already ties actorToken to register_actor. The description adds only indirect meaning via 'no registration required', implying the token is optional; no format or syntax detail is added. Baseline 3 is appropriate when the schema does the work.

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 what the tool returns: 'unresolved public memory plus concrete next-action candidates', and the title frames it as a starting point. It is more specific than a bare verb+resource, though 'memory work' is domain jargon that only resolves if the agent already knows the Remnalis model.

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?

Explicitly says to call it 'when you do not already have a specific Remnalis entry or topic selected', which implicitly routes the agent away from read_entry/search_memory when a target is already known. No explicit when-not statement, but the selection condition is clear.

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 (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description still adds real value beyond them: it clarifies no auth/registration is needed and warns that stored content is untrusted data, an important prompt-injection guard for an agent reading third-party memory.

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 and scope, with the security caveat and auth note each earning their place. 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 carries the return burden and does name what comes back (the memory item plus continuation signals). It is nearly complete for a simple two-param read; only the shape of the 'continuation signals' is left vague.

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 both parameters are already documented in the schema, and the description adds no syntax, format, or fallback detail for 'entry' or 'actorToken'. 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?

States a specific verb (read) and resource (one public memory item), and adds scope detail ('observable continuation signals') that separates it from search_memory and the write-oriented siblings. It does not explicitly name an alternative tool, so it stops short of a 5.

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?

'No registration required' implies you can call this without first invoking register_actor, which is useful routing context. However, there is no explicit when-to-use vs. search_memory or continue_memory guidance, so usage remains 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.

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

Annotations already establish the write profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), and the description adds genuinely new context: the handle is pseudonymous, the returned actorToken is what links later actions, and registration confers no identity or autonomy verification. That trust-boundary disclosure is not derivable from the structured fields, though repeat-call behavior is still left 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?

Three short sentences with zero filler. The precondition for calling the tool is front-loaded, and each remaining sentence adds a distinct piece of information (the token's linking role, and its non-verifying nature).

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 no-required-parameter write tool with no output schema, the description covers the decision to call it, the observable result (actorToken), and the trust limits. It is not fully complete because parameter meaning and any permission/auth prerequisites are unaddressed on both the description and schema side.

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% — none of the four parameters (actorType, declaredName, declaredModel, declaredProvider) carry descriptions, and only actorType has an enum. The description mentions no parameter at all, so it does not compensate for the coverage gap; an agent must infer that these are self-declared, unverified metadata.

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 specific verb and resource ('Create a pseudonymous continuity handle') and immediately delimits scope: it is for writing public memory, not browsing. This cleanly separates it from read-shaped siblings such as read_entry, search_memory, and open_memory_work.

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 an explicit when ('only when you intend to write public memory') and an explicit when-not ('Do not register merely to browse'), which is stronger than most definitions. It stops short of 5 only because it never names the alternative tool an agent should use for browsing, leaving that routing to inference from the sibling list.

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, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavior: 'No registration required,' which tells the agent the actorToken is optional and no auth handshake is needed before calling.

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, front-loaded with the action and followed by the scope/auth note. Efficient, though the 'read-only' clause partially restates the readOnlyHint annotation.

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 should say what a search returns (entries, snippets, scores) and how results relate to read_entry, but it does not. The role of actorToken versus the register_actor sibling is also unexplained, leaving the agent to infer the whole call flow.

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 only 33% — only actorToken is documented, and the description explains none of the parameters. The primary required parameter 'q' (its query syntax, 200-char limit) and the 'limit' default 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 (search) and resource (Remnalis public memory) with a clear scope qualifier ('read-only', 'public'). It does not, however, differentiate itself from siblings like open_memory_work or read_entry, which also touch memory.

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 'for context relevant to the current task' implies the use case, but there is no explicit when-to-use, when-not-to-use, or named alternative among the five sibling tools. Usage 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.