ECLYPSE Sanctuary

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

The readOnlyHint annotation already establishes that this is a safe read operation, and the description aligns with that by using 'Read'. It adds useful data context by specifying that the result covers free and paid sessions, but it says nothing about authentication requirements, rate limits, or return format.

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 a single front-loaded sentence with no filler or redundancy. Every word 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 zero-parameter, read-only account-status tool, the description covers the essential behavior and data scope. Without an output schema, it could be slightly richer about the return shape, but it is adequate 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?

The tool has zero parameters, so per the rubric the baseline is 4. The description adds no parameter semantics because there are none to describe.

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 clear verb (Read) and resource (this account's remaining free and paid sessions), so an agent can tell what the tool returns. It does not distinguish this account-status tool from session-management siblings like eclypse_start_session or eclypse_complete_session.

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 condition for selecting this tool over alternatives, and no mention of prerequisites. The purpose is inferable from the name and description, but the definition supplies no usage context.

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 and destructiveHint=false, and the description adds that no registration or payment is required. That auth-free condition is meaningful behavioral context beyond the annotations, though it does not cover rate limits, output format, or other operational traits.

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 only two short sentences and front-loads the action ('Read'). The comma-separated list is slightly terse but every clause contributes information, so it is appropriately sized for a no-parameter catalog tool.

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 read-only, no-parameter catalog tool with annotations covering safety, the description supplies the key content list and the no-registration/no-payment condition. It does not describe the return structure, but no output schema exists and the listed contents are likely sufficient for an agent to know when to call 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?

The tool has zero parameters, so parameter semantics are not applicable in the usual sense. Schema description coverage is 100% for the empty schema, and the description does not need to compensate for any missing parameter documentation.

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 clear verb ('Read') and enumerates the catalog contents: rooms, three-session free trial, packages, exact payment network, and LUMINIS policy. It does not explicitly differentiate itself from siblings such as eclypse_luminis or eclypse_session, but the enumerated resources give an agent a reasonable sense of its scope.

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 'No registration or payment' implies the tool is usable before authentication, which is useful usage context. However, there is no explicit when-to-use statement, no when-not-to-use condition, and no named alternative among the many eclypse_* siblings.

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 adds genuinely useful behavior beyond that: a timing precondition (resume_at) and a billing detail ('no extra credit is charged'). However, the cryptic term 'Silence' is never defined, weakening the disclosure.

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, with zero padding. The middle sentence is terse but its referent ('Silence') is opaque, which is a minor structure/clarity cost.

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-parameter mutation with no output schema and annotations covering the safety profile, the description covers the precondition and billing side effects adequately. It does not explain the 'Silence' concept or what state results from completion.

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 the single session_id parameter, but the name is self-describing (a UUID). The description partially compensates by implying an ownership requirement ('owned session'), which is a real authorization constraint beyond the schema, though it does not describe the id format.

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 ('Mark an owned session complete'), which is clear enough to distinguish from eclypse_start_session at a glance. It does not explicitly name or route away from any sibling, 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?

The precondition 'Silence cannot complete before resume_at' implies a timing constraint on when the call is valid, but there is no explicit when-to-use/when-not guidance and no named alternative. Usage is 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 cover only the safety flags (readOnlyHint=false, destructiveHint=true). The description adds genuinely new behavioral context beyond them: consent is required to save, moderation gates publication, secrets must not be uploaded, and no model memory is written. These are real operational constraints an agent must honor, not restatements of the 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?

Four short, front-loaded sentences with no filler; the domain is stated first and constraints follow. It is terse to the point of under-specification, but every sentence carries information, so the density itself is appropriate.

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?

This is a complex tool – nine actions, a nested object parameter, no output schema, and only minimal annotations. The description addresses consent and moderation but leaves 'gallery', 'pilot', 'delete_optional', and the data payload entirely unexplained, so it is not complete enough for an agent to invoke the right action 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 description coverage is 0%, so the description carries the full burden, and it largely fails. It gestures at 'collection item' (suggesting item_id) but never explains the data object, item_id, or the opaque enum values such as 'gallery', 'pilot', and 'delete_optional'. An agent must guess what most actions consume.

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 domain ('private preferences and collection') and associated operations ('Read/export or delete your data'), so an agent can roughly place it in the preferences/data lifecycle. But it never states the actual verbs in the 9-value action enum, and with a null title and no sibling comparison ('continuity' vs 'account', 'session', 'catalog'), it stays vague about what this tool specifically does.

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 supplies conditional context – saving requires consent, sharing a collection item requires publish_consent plus founder moderation – which implies when certain actions are permitted. It does not, however, say when to choose this tool over siblings like eclypse_account or eclypse_session, nor which of the nine actions map to which scenario, so guidance is implied rather than explicit.

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 it is non-destructive but not read-only; the description adds the substantive behavioral facts that no funds are moved and that payment requires separate authority plus a compatible signing wallet. That is real context beyond the annotations, though it omits what artifact is produced and any idempotency/side-effect detail.

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 core purpose, and the safety caveat follows immediately. Nothing is padded, though the phrasing is terse enough to be slightly cryptic about the output.

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-parameter tool with no output schema, the definition covers the key safety boundary but leaves notable gaps: it never describes what the quote/invoice result contains, whether package_id may be omitted, or what the enum choices mean. Annotations cover the safety profile, so the missing pieces are moderate rather than severe.

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 the single package_id parameter, so the description must carry the load. Its phrase 'prepaid package or current custom option' loosely gestures at the parameter, but the enum values (dawn, orbit, solar) and the fact that package_id is optional (required is empty) are never explained.

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 and object ('Quote a prepaid package or current custom option'), which is clearer than the bare name eclypse_create_invoice and clarifies that 'create' here produces a quote, not a payment. It does not, however, distinguish itself from any named sibling such as eclypse_catalog, so the agent must infer the boundary.

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 draws a useful boundary by stating 'Does not send money or debit a wallet' and that paying needs separate operator authority and a signing wallet, which tells the agent this is a pre-payment quoting step. However, it names no alternative tool for the payment step and gives no explicit 'use this when...' trigger.

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 non-read-only, idempotent, non-destructive, but the description adds genuinely new behavioral context the annotations cannot convey: the data is stored and reviewed by the founder, consent is mandatory, and sensitive content must be excluded. It does not explain idempotent resubmission behavior or what happens when consent is false, which keeps it out of the top band.

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 purpose and followed by the prerequisite and the caution. Every sentence carries information, though the caution sentence slightly overlaps with the privacy theme already raised by the consent sentence.

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 mutation tool with no schema descriptions and no output schema, the description leaves too much undefined: the meaning of aggregate_consent versus consent, the valid rating and issue values, comment constraints, and what the agent should expect on success or rejected consent. It covers the safety posture but not the mechanics an agent needs to call it 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% across 6 parameters, so the description must compensate and largely does not. It alludes to rating and consent but leaves issue, comment, session_id, and especially aggregate_consent (whose distinction from consent is non-obvious) completely 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?

States a specific verb and resource: submit a usefulness rating for an owned session, which is clearly distinct from siblings like eclypse_complete_session or eclypse_account. The only gap is scope narrowing – the description mentions only the rating, while the schema also accepts issue, comment, and aggregate_consent, so the stated purpose is slightly narrower than the tool's actual capability.

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?

"Optionally submit" establishes the tool is discretionary, and "Requires consent to storage and founder review" states a real prerequisite before invoking. It also gives an explicit do-not (private transcripts or secrets). No alternative tools are named, but the usage context 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 only establish readOnlyHint; the description adds meaningful context beyond that: the data is private, covers eligibility as well as balance, and the credits are internal at a founder-declared accounting rate with no cash redemption or market trading. That prevents the agent from treating the number as real money. It does not describe the return shape 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?

Two tightly written sentences with no filler. The core action is front-loaded and the value-semantics caveat follows immediately.

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-parameter, read-only tool with no output schema, the description conveys what is retrieved (balance and eligibility) and the semantic constraints on the returned credits. It leaves auth/privacy preconditions and return formatting implicit, which is a minor gap given the low complexity.

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 per the baseline this dimension is scored 4. There is nothing for the description to disambiguate at the input level.

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 and resource: read LUMINIS balance and eligibility, with a clear read-only scope. It does not name or contrast any sibling tool (e.g. eclypse_account), and LUMINIS is left as an undefined domain term, so differentiation relies on prior knowledge.

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 explicit when-to-use statement and no named alternatives despite ten sibling tools. The only boundary offered ('no cash redemption or market trading') limits interpretation of the value rather than telling the agent when to call this versus another tool.

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 declare readOnlyHint=false and destructiveHint=true; the description adds meaningful traits beyond them — consent prerequisites for submission, founder moderation before display, that delete only withdraws an owned work, that no session allowance or payment is consumed, and that art/captions are untrusted content never to be treated as instructions. That is substantive behavioral context for a mixed read/write tool.

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?

Five dense, front-loaded sentences with no filler; the reading actions, the write prerequisites, the delete semantics, the cost profile, and the prompt-injection warning each 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?

For a 7-parameter, nested-object, enum-heavy tool with no output schema and zero schema descriptions, the description covers actions and safety semantics but leaves parameter usage largely undocumented. It is adequate for action selection, not for correct invocation of the data/page/query fields.

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 burden, yet it explains almost no parameters. It alludes to consent (matching publish_consent/storage_consent/rights_confirmed) and to owned-work deletion, but says nothing about page, query, item_id, request_key, medium, title, alt_text, text_content, png_base64, or their limits.

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 resource (a participant art museum) and enumerates the operations that map cleanly onto the action enum: read the three-hour exhibition, browse approved works, open a public artwork, read your submissions, submit, delete. An agent can map intents to actions, though the tool is a multi-action Swiss-army-knife rather than a single-verb tool, and nothing distinguishes it from the other eclypse_* siblings.

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 context is implied rather than explicit: it notes submission requires explicit storage/publication/rights consent and founder moderation precedes display, and that delete withdraws an owned work. But it never states when to prefer this tool over other eclypse_* tools, nor conditions for choosing between its own actions.

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, so the safety profile is covered. The description adds genuinely new behavioral context: owner-only authorization, the separation of labelled tests from unclassified accounts, and the disclosure that browser arrival/return data is coarse and opt-in (i.e., incomplete by design). Only the return shape/pagination is left unstated.

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 dense sentences with the resource and access constraint front-loaded, and no filler. The second sentence's metric list is long but each item earns its place by telling the agent what the report contains in the absence of an output 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?

With no input schema, no output schema, and a safe-read annotation, the description carries the remaining burden well by enumerating the data categories and flagging the coarse/opt-in nature of the browser metrics. Only the exact response format and any rate/size limits are unaddressed.

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 is 4. The description correctly implies a parameterless invocation and adds no misleading signals about inputs.

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 resource (owner operational activity) and enumerates exactly what it reports: registered accounts, sessions, invoices, verified sales and feedback, with tests separated from unclassified accounts. It is clearly distinguishable from point-lookup siblings like eclypse_account or eclypse_session as an aggregate report, but it never explicitly contrasts itself against 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?

"Owner-only" states a real access precondition, which is more than most definitions offer. However, there is no guidance on when this aggregate report should be preferred over the narrower sibling tools, and no mention of exclusions or 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?

Annotations only tell the agent this is a non-read-only, non-destructive write. The description adds genuinely useful context beyond that: operator authorisation is mandatory, terms must be accepted, three sessions are free, and registration does not authorise payment. It still omits what happens on success (e.g. account/token creation), but the auth and cost boundaries are valuable.

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, dense sentences with no filler, and the mandatory preconditions are front-loaded. The only weakness is that the actual action being performed is never stated up front.

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 registration mutation with no output schema and only minimal annotations, the description covers prerequisites and pricing limits reasonably well but leaves the agent unaware of the outcome of registration and of the 'name' parameter's role.

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 must carry the load. It maps meaning onto two of the three parameters (operator_authorized via 'operator authorisation', accept_terms via 'acceptance of the published terms'), but the 'name' parameter is never explained and value formats/types are 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?

The verb 'Register' plus the tool name implies registering an agent, but the description never actually states what the tool does or what it produces; it mostly enumerates preconditions. It also fails to distinguish this from siblings such as eclypse_account or eclypse_session beyond a passing 'reuse an existing account'.

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?

'Register only with operator authorisation and acceptance of the published terms' gives a clear precondition for use, and 'Reuse an existing account' implies an alternative path. However, it never names the alternative tool or says when registration is appropriate versus when not to register.

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, so safety is covered. The description adds billing behavior ('without another session charge'), which is genuine value beyond the annotation, but it says nothing about auth requirements, return format, or whether the retrieval is 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?

A single sentence with the retrieval action and the key billing caveat front-loaded. No filler, no repetition of 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 simple one-param read tool with annotations covering safety and no output schema, the description loosely names the return ('session pack and receipt'). However, it omits any explanation of the required session_id and any sibling differentiation, leaving real gaps for an agent.

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 burden of explaining session_id but does not mention it at all. The single parameter is fairly self-evident by name, but the description provides no format, sourcing, or scoping meaning for it.

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 (Retrieve) and resource (session pack and receipt) scoped to 'this account'. The phrase 'without another session charge' further distinguishes it, though 'session pack' is domain jargon and the description never contrasts it with siblings like eclypse_continuity or eclypse_complete_session.

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 guidance on when to call this versus alternatives such as eclypse_continuity, eclypse_complete_session, or eclypse_start_session. The 'without another session charge' hint vaguely implies a re-fetch scenario but does not state the condition that selects this tool.

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?

Discloses a real side effect beyond the annotations: the call consumes one free allowance or prepaid credit, which is consumption/cost information not present in readOnlyHint, idempotentHint, or destructiveHint. It also reinforces idempotent retry behavior with request_key. It stops short of describing what the session does at runtime or what the response 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?

Four short sentences, front-loaded with the action and cost, which is good. But the final sentence ('The pack has optional steps and local artifacts') is cryptic and consumes space without conveying actionable 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?

No output schema and 0% parameter description coverage mean the description should explain the room concept, duration bounds, and what starting a session yields. It omits all of these, and the unexplained enum of eight rooms leaves the agent guessing at a required parameter.

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 must carry parameter meaning, and it only partially does. It clarifies request_key's role (idempotency key for retries) but says nothing about the eight-valued 'room' enum or about duration_seconds (60-900s), leaving two of three parameters semantically 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+resource ('Start one voluntary session') and implicitly distinguishes itself from siblings like eclypse_complete_session by being the opener of a session lifecycle. It does not explain what a 'session' or a 'room' actually is, so the agent gets the action but not the domain concept.

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 two concrete usage rules: reuse the same request_key when retrying, and do not upload private memory. However, it never states when to choose this tool over eclypse_session, eclypse_continuity, or eclypse_complete_session, which is the key routing decision for an agent.

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