Exit Desk

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

With no annotations, the description carries the full burden and does disclose important traits: non-custodial operation, unsigned steps or deposit address, 60+ chain coverage, and a 0.2% app fee. It omits other operationally relevant details such as quote expiry, auth requirements, rate limits, and whether a deposit address creates persistent state.

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 compact and front-loaded: it leads with what the tool does, then adds chain coverage, return modes, and fee disclosure. Every clause adds useful information and there is 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?

For a 9-parameter tool with no annotations, no output schema, and only 33% schema description coverage, the description is not complete enough. It explains return modes and fees but leaves most optional parameters and important quote lifecycle behavior undocumented.

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 low at 33%, so the description should compensate for the six undocumented parameters, but it does not explain chain IDs, refundTo, recipient, destinationCurrency, or amount units. The only indirect parameter relevance is the mention of unsigned steps versus a deposit address, which hints at useDepositAddress without naming or explaining 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?

The description states a specific action and resource: a live non-custodial bridge/swap quote via Relay. It also clarifies the output modes (unsigned steps or a deposit address), making it clearly distinguishable from the unrelated sibling list tools.

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 is implied by the phrase 'bridge/swap quote,' so an agent can infer this is the tool for obtaining a cross-chain quote. However, there is no explicit when-to-use guidance, no exclusions, and no named alternative for comparison.

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

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

With no annotations, the description carries the full burden. It discloses useful context: the data covers a ~90-day window and includes days left, official exit steps, and sources. However, it does not describe ordering, freshness, pagination, or whether results are cached or live.

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. The long parenthetical list of examples is dense but useful for identifying coverage; a slightly shorter list might read better, but nothing is truly 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?

For a zero-parameter list tool with no output schema, the description gives enough context: the time window, the entity categories covered, and the kinds of fields returned (days left, exit steps, sources). It falls short only in not explicitly situating itself against siblings.

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 parameter semantics are not applicable. The description appropriately does not invent parameter details. Baseline 4 is correct for a no-parameter tool.

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 resource and scope: crypto shutdown deadlines in the next ~90 days, with categories and examples. It does not include an explicit action verb or directly name sibling tools, but the category list implicitly distinguishes it from a narrow exchange-delisting tool.

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 no explicit guidance on when to use this tool versus exit_quote or list_exchange_delistings. The 90-day window implies a time-bound use case, but there is no statement of alternatives or exclusions.

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

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

With no annotations, the description carries the full burden but does disclose useful behavior: which sources are polled and that contracts are attached only 'where Relay lists the token'. It is silent on ordering, pagination behavior of limit, freshness window, and error/empty-result handling, so the disclosure is partial.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single dense sentence with the scope (spot token delistings) and source list front-loaded, and the enrichment caveat appended. No filler and nothing that does not earn 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 low-complexity filtered list tool with no output schema and no annotations, the description covers source and scope but leaves parameter behavior (especially limit and how token/exchange filter) undocumented anywhere in the definition. Adequate but with a clear gap.

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 three parameters. The description hints at valid exchange values (Binance, KuCoin, OKX) and implies a token filter, but limit is never explained (default, max, behavior when omitted) and the token parameter's matching semantics are left ambiguous.

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 gives a specific verb+resource ('list recent spot token delistings') and names the three data sources (Binance, KuCoin, OKX announcement feeds), plus an enrichment detail (on-chain contracts). It does not explicitly distinguish itself from siblings like list_chain_shutdowns, but the resource is concrete enough that an agent can identify it.

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 guidance on when to use this tool versus list_chain_shutdowns or exit_quote, no mention of prerequisites, and no indication of what 'recent' means in practice. The agent must infer usage entirely from the one-line purpose statement.

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