SeenRelay

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

Annotations already declare the tool read-only, non-destructive, and idempotent. The description adds meaningful context beyond that: it is a preflight rather than a verification step, it never browses or verifies externally, and it is policy-conditional about evidence reuse. It could be more explicit about what the tool actually returns, but no contradiction exists.

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 core purpose and remains compact at three sentences. The list of costly operations is somewhat repetitive, but each clause adds context about when the preflight is valuable. No unnecessary padding.

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?

The usage context is well covered, and annotations plus the rich nested schema carry much of the structural burden. However, there is no output schema and the description never states what check_fact returns (e.g., fresh/stale, reusable boolean, cost estimate), nor does it explain the role of max_age_seconds. This leaves a meaningful gap for an agent deciding 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?

Schema description coverage is 0%, so the description carries the burden of explaining parameters, but it never names fact, known_value, or max_age_seconds. It hints at known_value via 'caller already has a known value' and at source-backed facts, but max_age_seconds is entirely unaddressed. The description does not compensate for the lack of schema descriptions.

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 (cost preflight / freshness check) on a specific resource (source-backed fact) and clearly distinguishes it from external validation by stating 'SeenRelay never browses or verifies externally.' It also differentiates from the sibling observe_fact through the 'OBSERVE for later runs' instruction.

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 explicitly says when to use the tool: before paid web search, metered scraping, browser/extraction, rate-limited APIs, or multi-step validation when the caller already has a known value. It also gives the when-not condition: if evidence is not reusable, validate normally and OBSERVE. This is strong, actionable routing guidance.

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 readOnlyHint=false, the write nature is already signaled, and the description adds valuable behavior context: the optional Ed25519 proof 'establishes key possession and continuity, not truth or real-world independence,' and the observation is meant to cache validated results. It does not contradict the annotations and meaningfully expands on their sparse signal.

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 earning its place: the core action, the critical hearsay prohibition, and the nuanced clarification of what the proof does and does not establish. It is tightly front-loaded and contains 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?

The high-level purpose and proof caveat are well covered, but this is an 8-parameter tool with nested objects, no output schema, and zero schema description coverage. The description does not address idempotency, observer identity, source validation mechanics, or what happens on duplicate submits, leaving an agent with meaningful gaps 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 schema description coverage is 0%, so the description bears the burden of explaining parameter meaning, but it only touches on the proof parameter ('Optional Ed25519 proof') and never explains fact, value, observer_id, idempotency_key, source_validator, or observed_at. The schema names parameters, but the description does not compensate for the lack of parameter-level semantics.

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—'deposit the observed result' after 'source-backed validation'—and makes clear this is a contribution/write operation, not a retrieval one. Its language contrasts naturally with the sibling tool check_fact, so an agent can distinguish 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?

The description gives an explicit precondition: the caller must 'independently perform a source-backed validation' before depositing. It also says when the deposit is useful (avoiding 'paid or slow work' when policy permits) and warns 'Never OBSERVE hearsay.' It stops short of naming alternatives or explicitly saying when not to use the tool, but the guidance is clear.

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