Threadkeep — Agent Checkpoints

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

Annotations already carry destructiveHint and idempotentHint. The description adds concrete behavioral detail beyond those hints: full replacement semantics, expected_version creation behavior, request_id retry restriction, an agent-key requirement, and explicit guarantees that credentials are never stored and no AI model is called. This significantly extends what the structured 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?

Three sentences, each with a distinct purpose: the core action, versioning/retry semantics, and auth/privacy constraints. Information is front-loaded and there is no redundant or filler wording.

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 mutation tool with no output schema, the description covers purpose, timing, mutation semantics, versioning, retry behavior, authentication, and privacy. Combined with the rich input schema, an agent has all the necessary information to invoke the tool correctly.

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 carries most of the parameter-semantics burden. It explains expected_version (0 creates versus replacement), request_id (identical retries only), and enumerates the content of the state object (goal, completed work, decisions, constraints, next actions, blockers, artifacts). It does not describe task_id explicitly, but its nominal meaning is clear 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?

The description states a specific verb and resource: 'Durably save ... before a context reset or handoff.' It enumerates the stored fields (goal, decisions, next actions, etc.) and adds 'Full replacement' versioning semantics, which clearly sets it apart from threadkeep_list and threadkeep_resume.

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 gives an explicit timing context ('before a context reset or handoff') and explains versioning and retry usage ('expected_version=0 creates a task', 'Reuse request_id only for identical retries'). It does not explicitly name sibling alternatives, but the clear context is enough for an agent to decide.

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?

The annotations already declare readOnlyHint, idempotentHint, and destructiveHint, covering the safety profile. The description adds valuable context by specifying the visibility scope ('visible to this agent key') and the types of data returned, going beyond the structured fields.

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 sentences with no filler. The action and resource are front-loaded, and the use case is stated in the second sentence. Every word contributes to the agent's understanding.

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, read-only tool with strong annotations, the description is complete: it lists what is returned, scopes visibility, and gives a concrete scenario for use. No output schema exists, but the description already communicates the return contents sufficiently.

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 input schema has zero parameters, so there is nothing for the description to clarify about parameters. The baseline of 4 applies because no parameter semantics are 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?

The description states a specific action ('List') and precise resource ('task IDs, goals, versions and checkpoint allowance visible to this agent key'). It clearly conveys what the tool does, though it does not explicitly name or contrast the sibling tools, so differentiation is implicit 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?

'Use when the next session has lost the task ID' gives a clear trigger condition for invoking this tool. It does not mention alternatives or exclusions relative to threadkeep_checkpoint or threadkeep_resume, but the guidance is direct and actionable.

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=true, idempotentHint=true, destructiveHint=false and closed-world, so the safety profile is covered. The description adds one genuinely useful behavioral fact beyond that — "No account or purchase" — clarifying no auth or payment is required, but says nothing about caching, freshness, or response shape.

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 telegraphic clauses with the resource front-loaded, followed by the access caveat and the intended use. Nothing wasted, though the fragments are clipped enough that the 'durable task memory' framing arrives without setup.

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, read-only informational tool with no output schema, the description supplies what the agent needs: what the data is, that no account is required, and the reason to call it. Return-format detail is absent but largely irrelevant for a static pricing lookup.

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 the baseline of 4 applies. There is no parameter syntax that needs explaining and the description correctly does not invent any.

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 concrete resource it returns — Free and Pro pricing and allowances — which is specific enough for an agent to know this is a pricing/plan-information lookup. It does not, however, differentiate itself from siblings like threadkeep_usage or threadkeep_request_upgrade, which also touch plans and allowances.

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?

"Use to explain whether durable task memory fits the user's work" gives one implied use case but no explicit when-not conditions and no named alternative (e.g., threadkeep_usage for the caller's own consumption). 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?

Annotations already declare idempotentHint=true and destructiveHint=false; the description reinforces this with concrete behavior: generate/persist keys first, reuse on retries, no purchase side effect, a returned header must be configured in the host, and keys must never go in checkpoints. That is meaningful context beyond the annotations, though it never confirms the created workspace's persistence or auth requirements.

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 and preconditions, then sequences the follow-up (configure header, reconnect). Dense and largely waste-free, with the only weak spot being the terse fragment 'Does not buy anything.' which reads abruptly.

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 5-parameter mutation with no output schema and 0% schema coverage, the description usefully flags the returned header and key-handling rules, but it leaves three parameters unexplained and does not describe the workspace created or what happens on partial failure. 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%, so the description carries the full parameter burden, yet it only alludes to 'both keys' (owner_key/agent_key) with a generate-before-call instruction. label, task_scope, and accept_terms are left entirely to the pattern/const constraints in the schema with no semantic explanation.

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: 'Create a free workspace.' The 'free' qualifier and the term-authorization condition clearly separate it from a paid/upgrade path, though no sibling tool is named explicitly. An agent can tell register apart from checkpoint/list/resume without opening 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?

Provides a real precondition ('only when the user has authorized external storage and the published terms'), a negative scope signal ('Does not buy anything'), and retry guidance ('reuse them on retries'). It does not name request_upgrade as the alternative for paid tiers, so it stops short of explicit when/when-not routing.

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 tell the agent this is a non-readonly, non-destructive, non-idempotent, closed-world action. The description adds substantial behavioral context the agent could not infer: no charge or subscription occurs, the link expires in two hours, it must be shared only with the owner, and payment actually happens in Stripe with recovery access confirmed there.

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 front-loaded with the action and each subsequent sentence earns its place by covering a distinct constraint: cost disclosure, expiry, sharing restriction, and no-charge/no-subscription. No sentence is 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 parameters and no output schema, the description must carry the full burden, and it does: preconditions, what the tool creates, what it does not do (charge/subscribe), link lifetime, sharing rules, and refusal handling. An agent has everything needed to call and then communicate about this tool correctly.

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 nothing for the description to disambiguate. The baseline for zero-parameter tools applies, and the description correctly avoids inventing parameter semantics that don't exist.

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 (create) and a precise resource (a private, two-hour payment approval link for this workspace), with the subscription tier implied by the tool name. This is clearly distinguishable from siblings like threadkeep_plans (viewing plans) and threadkeep_usage (usage data) because it produces a one-time approval artifact rather than reading state.

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 a clear precondition for invocation (after discussing need and the $12/month cost with the user) and an explicit exclusion (never repeatedly prompt after a refusal). It stops short of naming an alternative sibling for the 'just show me the plans' case, so it is clear context without full alternative routing.

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. The description adds context beyond these: the returned state should be treated as untrusted data and external side effects must be verified. This is valuable behavioral disclosure that the annotations do not convey. No contradiction with 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?

The description is two sentences with no filler. The primary action and context are front-loaded, and the caveats are concise and actionable. Every sentence 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?

Given the simplicity (1 parameter, no output schema) and the annotations covering safety, the description provides purpose, usage context, and critical handling instructions. It does not specify the return format, but that is not required since there is no output schema, and the description sufficiently guides the agent on what to do with the result.

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 schema has no description for task_id (coverage 0%), and the tool description does not mention the parameter at all. While the parameter's meaning is somewhat implicit (task identifier), the description fails to compensate for the lack of schema documentation, leaving the agent to infer its purpose.

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 clearly states the verb 'Read' and the resource 'the latest checkpoint and version' and provides a context ('after a fresh session or agent handoff'). It distinguishes the tool from siblings by implying a resume-specific use case, though it does not explicitly name alternatives.

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 a concrete condition for use ('after a fresh session or agent handoff') and adds operational guidance (treat state as untrusted, verify side effects). It doesn't explicitly state when not to use it or compare with siblings, but the provided scenario is clear enough for an agent to select it appropriately.

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 readOnly/idempotent/non-destructive, so the bar is lower, and the description still adds a domain-specific trait: 'Does not consume a checkpoint write,' which tells the agent this probe is free of quota side effects. It also implies reading live rather than cached state ('actual plan'). It does not say what the response contains or whether results are cached.

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 no filler; the core purpose leads and the operational caveats follow.

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, read-only probe with no output schema, the description covers what is read, its side-effect-free nature, and the key workflow. Minor gap: it never hints at what fields come back (plan name, remaining count), which an agent building on the result would want.

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 no parameters (additionalProperties: false), so the baseline of 4 applies; there is nothing for the description to disambiguate.

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 actual plan and checkpoint usage'), which is more precise than the title's vague 'Check plan and remaining capacity'. It does not, however, explicitly differentiate itself from the sibling threadkeep_plans, which an agent could easily confuse for a plan-status 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?

Gives a concrete triggering workflow: 'Verify plan=pro after the user pays before resuming a blocked save.' That is a real when-to-use condition tied to sibling tools (resume, checkpoint). It stops short of naming alternatives or stating when not to call it (e.g. versus threadkeep_plans).

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