Peerlytics

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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the safety profile is covered. The description adds a genuinely new behavioral trait beyond them: results are a bounded latest sample, not all-time totals, which shapes how an agent should interpret output. It stops short of describing pagination or the receipt-desk interaction.

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 tight sentences with no filler, and the core purpose is front-loaded. The receipt-desk clause is slightly obscure and costs a little clarity, but the overall structure is efficient.

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 and 0% parameter documentation, the description must carry more weight. It partially does by stating the result is a bounded sample, but it leaves both parameters and the return shape under-specified for a tool with two inputs and optional ('address') filtering.

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 two parameters. Neither 'limit' (its 1-25 bounds) nor 'address' (an address filter) is explained in the description; a reader cannot tell whether 'address' scopes the query to a specific account. The description does not compensate for the coverage gap.

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 recent public Peer protocol activity on Base.' However, the trailing clause 'open its interactive receipt desk' blurs the purpose by suggesting a UI/desk-opening action rather than a read, and the sibling peerlytics_receipt is never named to disambiguate.

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 guidance on when to use this versus the sibling peerlytics_receipt. The only constraint given ('bounded latest sample, never all-time totals') describes output scope, not when-to-use conditions or prerequisites.

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, openWorld, and non-destructive, so the safety profile is covered without the description's help. The description does add genuine semantic context by warning that past fills are not a quote and listed liquidity is not a guarantee of a fill, which shapes how results should be interpreted, but it says nothing about return shape, freshness windows, or empty-result behavior.

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 tight sentences with the capability, the filters, and the caveats in that order; nothing is padded. The phrase "by route" is slightly opaque, and the format examples could have been folded into a single clause, but the front-loading is sound.

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-parameter, optional-filter read tool with no output schema, this is close to sufficient: it says what data comes back at a high level and how to narrow it. A brief note on combining filters or on what an empty response means would close the remaining 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%, so the description carries the full burden, and it does: it names both parameters, supplies example values ('GBP', 'revolut'), and makes the casing conventions explicit, which the bare regex patterns alone would only hint at. What it does not clarify is the OR-versus-AND relationship when both filters are supplied, nor the default behavior with zero parameters.

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 Peer protocol market data") and enumerates what is returned: 30-day seller rates from past fills and current listed USDC liquidity. It does not explicitly differentiate itself from sibling tools (peerlytics_activity, peerlytics_receipt), so the agent must infer the boundary from the names 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?

Gives concrete filtering guidance, including valid value formats ("ISO currency code (GBP)", "lowercase platform id (revolut)"), which implicitly tells the agent how each filter is used. It stops short of stating when to prefer this tool over the sibling activity or receipt tools, or whether the two filters can be combined.

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 (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint), so the bar is lower, yet the description adds real context: it returns indexed settlement evidence, timestamps and provenance, and it deliberately withholds payee/payment identifiers. That data-minimization behavior is not derivable from annotations or schema.

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 compact sentences, front-loaded with the lookup action before the behavioral guarantees. Every clause carries weight, though 'Preserves indexed settlement evidence, timestamps and provenance' is slightly jargon-dense.

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 usefully signals what comes back (settlement evidence, timestamps, provenance) and what is withheld, while annotations handle the safety profile. Error/not-found behavior for an unknown hash or id is the only meaningful omission.

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 burden, and it partly does by mapping the two accepted identifier forms ('intent hash' vs 'chain-qualified deposit identifier') onto the kind enum of intent/deposit. It does not clarify the required id format, length bounds, or the 'chain-qualified' syntax, leaving gaps for a low-coverage 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 ('Look up') and the resources it accepts (a public intent hash or chain-qualified deposit identifier), which is concrete enough for an agent to recognize a receipt lookup. It stops short of naming or contrasting with the sibling peerlytics_activity, so sibling differentiation is absent.

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 clause 'never initiates a financial action' implies this is a read-only retrieval path and sets a boundary on use, but there is no explicit when-to-use guidance or routing to the alternative (peerlytics_activity). Usage is only 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.