Moltline Recall

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

Annotations already declare readOnly/idempotent/non-destructive, yet the description still adds substantial context beyond them: the since/until filtering semantics, exponential decay via half-life, an error contract (returns {error: ...} rather than raising a protocol error), and the retry-safety guarantee. The premium licensing constraint is also disclosed.

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 purpose, then semantics, then a request/response example, then the error and idempotency contract — every block is purposeful. The inline JSON example of input and return payload is slightly redundant given the output schema exists and could be compressed, but it does show the dropped/decayed counters concretely.

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-parameter, nested-graph tool with a premium gate, the description covers purpose, filtering semantics, decay, error behavior, and retry safety. Return shape is partly described despite an output schema existing, so nothing an agent needs to call or recover from a call 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 coverage is 100%, so the baseline is 3, but the description adds real meaning: a worked example showing as_of as a concrete ISO date and half_life_days = 180, plus the explanation that a two-year-old belief should not weigh the same as last week's, which conveys the intent of decay. It does not clarify that half_life_days=0 disables decay without leaving that 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: viewing the memory graph as of a given date, with optional age-based confidence decay. It also names the sibling it is not (graph_diff) and the condition that separates them, so an agent can route without opening any 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 an explicit positive trigger ("Use when the answer depends on when you ask") and an explicit exclusion pointing to the correct alternative ("Not for what changed between two points - that is graph_diff, which does not need dates at all"). It also flags the PREMIUM license requirement up front, which is a gating condition for use.

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 read-only, idempotent, non-destructive, and closed-world, so the description earns credit for adding beyond them: it specifies that malformed input returns an {"error": ...} payload rather than a protocol error, and that retry after correction is safe. It also discloses the exact ranking rule and the shape of the result.

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?

It is front-loaded with purpose, then usage, then mechanics, and every block carries information. The opening metaphor ("the part that still earns its place") is slightly decorative, but it is immediately grounded and costs only one clause.

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?

Even with an output schema present, the description supplies the return shape, the error contract, and the ranking semantics an agent needs to predict behavior. For a nested-object, three-parameter compaction tool nothing material 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 coverage is 100%, so the baseline is 3; the description goes further by showing a concrete input example and spelling out the tiebreak chain (degree, then observation count, then name) that governs max_entities and the keep list. The case-insensitivity of keep is already in the schema, so no extra credit there.

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 a specific operation on a specific resource: rank entities by connectivity and observation count, retain explicitly named ones, drop the remainder plus their relations. It also distinguishes itself from graph_lint by role, so an agent can tell the two apart without opening either 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 states the trigger condition plainly ("Use when a graph has outgrown the context you can spend on it") and an explicit exclusion with the correct alternative ("Not for removing wrong facts - graph_lint finds those"). Both when and when-not are covered.

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, and non-destructive, but the description adds substantial context beyond them: the error contract (never raises a protocol error, returns {"error": ...}), and the guarantee that correcting input makes retry safe. This is exactly the kind of behavioral disclosure annotations cannot 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?

The purpose and the free/cheap framing are front-loaded, and each paragraph (what it does, example I/O, when to use, when not to, error behavior) earns its place. Minor deduction for the marketing-ish "FREE" and the awkward mid-sentence line break in the second paragraph.

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-object-diff tool with an output schema, the description covers the remaining ambiguity – input shape, output shape, error handling, retry safety, and the boundary with graph_upsert. An agent has everything needed to call it correctly on the first try.

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% and both params are documented as "earlier" and "later" graph documents, so the baseline is 3. The description adds value with a concrete typical input example ({"before": {...}, "after": {...}}) and names the graph concepts the documents contain (entities, observations, relations), which the schema leaves opaque.

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: "Say exactly what changed between two versions of a memory," and immediately differentiates from the merge use case by naming graph_upsert. An agent can distinguish it from graph_at_time, graph_search, and graph_upsert without opening any 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 concrete when-to-use contexts (after an upsert to record what a session learned; between two agents to compare knowledge) and an explicit when-not-to-use with the correct alternative ("Not for merging the two - feed the differences back through graph_upsert"). Nothing 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 readOnly/idempotent/non-destructive, but the description adds genuinely new behavior: errors never surface as protocol errors and instead return {"error": "<what is wrong and how to fix it>"}, plus an explicit retry guarantee after input correction. The worked example output discloses the concrete response shape far beyond what the annotations convey.

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 purpose, then defect types, then a concrete example, then usage rules and exclusions. The large return-value example is somewhat redundant given an output schema exists, and the 'FREE.' fragment is stray, but no sentence is wasted overall.

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?

Covers purpose, defect taxonomy, example output, when-to-use, sibling exclusions, and error/retry semantics for a single-parameter read-only tool. An agent has everything needed to select and invoke it correctly without opening 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?

Only one parameter and schema coverage is 100%, so the schema already documents 'graph', and the description's {"graph": {...}} example adds little beyond that. The graph document is a nested open object, and neither schema nor description explains its internal structure, but with full coverage the baseline 3 is appropriate.

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+resource (lint a memory graph) and enumerates the exact defect classes it finds: dangling relations, orphan entities, near-duplicate names, contradictions. It is immediately distinguishable from graph_diff and graph_compact, which it names 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?

Gives both positive triggers ('before trusting a graph you did not build, or on a schedule as memory grows') and explicit exclusions with the sibling that handles each ('Not for comparing two graphs (graph_diff) and not for shrinking one (graph_compact)'). Nothing 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 cover read-only/idempotent/non-destructive, but the description adds substantial context beyond them: the tool never raises protocol errors and instead returns a structured {"error": ...} with a concrete example, plus a cost disclosure ('FREE') and an explicit retry-safety guarantee. It also discloses the match-scoring heuristic (word overlap in name/type/observations), which is real behavioral information an agent cannot get from 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?

Purpose and cost are front-loaded in the first line, and the sibling routing and error contract follow logically. The inline example JSON is long but earns its space by demonstrating scoring output; the closing 'read-only and idempotent' sentence partly restates the annotations and could be trimmed.

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 4-parameter tool with nested graph input, rich annotations and an output schema, the description covers purpose, alternatives, scoring behavior, hop expansion, error contract and retry safety. Nothing an agent needs in order to call it correctly or recover from a bad call 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 coverage is 100% and every parameter has a description with bounds and defaults, so the baseline is 3. The description goes beyond that by showing a concrete call shape ({"query": "acme renewal", "hops": 1}) and explaining what the resulting 'score' and 'why' fields mean, which makes the query and hops semantics tangible rather than abstract.

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+resource ('find what the graph knows about something') and immediately extends it with scope ('plus its neighbourhood'). It also names the two siblings it is not (graph_upsert for writing, graph_at_time for date narrowing), so an agent can discriminate without opening any 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 an explicit when-to-use ('Use to read memory back before answering') and two explicit when-not-to-use cases mapped to the correct alternatives. The scoring/hop rationale also tells the agent why a hops value is appropriate.

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 destructiveHint=false, but the description earns credit by adding the duplicate-suppression semantics, a concrete size-limit failure ("graph exceeds <value> entities; split it"), and the contract that errors are returned in-band rather than raised as protocol errors, making retry-after-correction safe. It also pre-empts the apparent tension between "write path" language and readOnlyHint by stating every call is read-only and idempotent.

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 key claim and the free/idempotent framing are front-loaded, and paragraphs are organized as purpose, behavior, alternatives, errors. Mild redundancy remains: the example return payload duplicates what the output schema already provides, and idempotency is stated twice.

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-parameter tool with an output schema, annotations, and complete schema coverage, nothing an agent needs is missing: purpose, sibling routing, example input/output, idempotency guarantees, size limits, and the error envelope are all covered.

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 baseline is 3, but the description adds a worked input example showing how pre-existing graph state composes with new entities, plus the merge/append behavior on observations. That gives an agent a concrete call shape the schema alone does not illustrate; only the relations parameter is 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?

"Fold new facts into a memory graph and get the whole graph back" names a specific verb (fold/upsert) and resource (memory graph), and immediately states the whole-graph return behavior that distinguishes it from an incremental writer. An agent can separate it from graph_search and graph_diff from the description alone.

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 designates itself "the single write path for memory" and rules out two alternatives by name: graph_search for selective reads and graph_diff for finding what a write changed. Both the when-to-use and the when-not-to-use are stated.

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