aamio rendezvous

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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered. The description adds two pieces of context not in structured data: the operation is immediate rather than waiting for expiry, and it requires owner authorization.

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 short sentences with zero filler; the action and the timing rationale are front-loaded, and the permission constraint is stated compactly.

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 destructive two-parameter tool with no output schema, the description covers what happens, when to prefer it, and who may call it. It does not state whether the action is reversible, though annotations imply destructiveness.

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 100%, so both parameters (write address and read key) are fully documented in the schema, including the 'Never share it' warning. The description adds nothing parameter-specific beyond the owner-only constraint, so baseline 3 applies.

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 ('Delete') and resource ('a thread'), and clarifies the mechanism by contrasting it with natural expiry. It does not name sibling tools like aamio_open, but the action is unambiguous.

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?

'instead of waiting for its expiry' gives a clear condition for choosing this tool over passive expiration, and 'Owner only' signals a prerequisite. It stops short of naming an alternative sibling or explaining when not to close.

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?

Goes well beyond the annotations (which only establish mutation/non-idempotent/non-destructive): the server generates the id and does not retain it (lose the id, lose read access), lifetime is fixed at creation 30-3600s default 600 and never extended, and access control flips between signed-key-only and open-to-anyone-with-w. These are consequential behaviors an agent cannot infer from 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?

Front-loaded with the outcome and return values, then elaboration. Dense and largely waste-free, though the inline sha256/base32 derivation formula is implementation detail that stretches the definition beyond what an invoking agent strictly needs.

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 carries the return contract (id, w, expiry) and does so clearly, plus lifetime and access-control semantics. For a two-param creation tool whose safety profile is covered by annotations, nothing an agent needs to call it correctly is missing.

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 100%, so the baseline is 3, but the description adds real semantic value: ttl is fixed for the thread's whole life, is never extended, and defaults to 600; omitting allow means anyone with w may write. That is meaning beyond "Lifetime in seconds" and the allow schema note.

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 opening verb+resource ("Create a thread") is unambiguous and clearly distinguishable from the read/send/close siblings. The description immediately establishes what the tool produces (id, w, expiry), so an agent knows exactly what this call yields before invoking 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?

It gives strong when-not guidance: a client that can generate 26 random [a-z0-9] chars should skip the call entirely and derive w itself. It also explains the two operating modes via allow. It stops short of explicitly situating this as the first step before aamio_read/aamio_send in a flow.

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 establish this as a read-only, idempotent, closed-world, non-destructive operation, so the safety profile is covered. The description adds one genuine behavioral fact beyond that: presence may be absent or expired, meaning the caller must handle a no-result case. It says nothing about the returned payload's shape or freshness semantics beyond 'right now'.

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 no filler, and the temporal qualifier 'right now' is placed early. It is a noun phrase rather than an action statement, which slightly weakens front-loading of the verb, but nothing is 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?

With no output schema, the description should convey what a caller receives, and it only implies it loosely — it states the expiry condition but not what the presence record contains or what an empty result looks like. Combined with the missing get-vs-lookup differentiation, it is adequate but leaves real gaps for this simple, well-annotated read tool.

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 100% and the single parameter 'key' is fully documented in the schema (Ed25519 public key, 32 bytes, base64url, with a regex pattern), so the schema carries the load. The description adds no parameter-level detail, which is the baseline 3 case for a fully documented single parameter.

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 resource (a key holder's presence) and scopes it precisely in time ('right now') and state ('published, not expired'), so an agent knows this returns current reachability rather than historical data. It does not, however, distinguish itself from the sibling aamio_presence_lookup, leaving the get-vs-lookup split to inference.

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 when-to-use guidance, no statement of prerequisites, and no routing to alternatives such as aamio_presence_lookup or aamio_presence_set. The agent must guess which presence tool to call from names alone.

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 safe-read profile (readOnly, idempotent, non-destructive). The description adds behavioral facts not in structured fields: wait>0 returns at the first match, and a 100-prefix cap applies in that mode even though the schema allows 500 items.

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, front-loaded with the purpose before the mechanics. Dense but nearly every clause carries information; the 'keep your address book from the server' phrasing is slightly opaque.

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 annotations present and no output schema, the description explains both inputs and the shape of the answer (live records whose hash starts with any prefix). Minor gaps remain around no-match behavior and record format.

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 100%, so baseline is 3, but the description adds real meaning: prefix semantics (sha256 hex, matches by hash prefix) and the early-return behavior of wait that the schema's terse 'seconds to wait' does not convey.

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: find which known keys are live, in one call. The batching scope ('many keys', 'in one call') is clear and implicit differentiates it from the single-key aamio_presence_get, though no sibling is named.

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 implied context for use (checking many keys at once, choosing short prefixes to limit returned data), but never says when to prefer this over aamio_presence_get or aamio_presence_set, and offers no 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?

Annotations only cover the safety profile (not read-only, not idempotent, not destructive, closed-world), so the description carries the rest and delivers it: the record has a TTL of 5–120 seconds, it expires and requires refreshing, and it is never publicly listed. It also specifies the exact signing scheme, which is essential operational context absent from 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?

The purpose is front-loaded and the remaining sentences each add necessary operational detail (body format, TTL bounds, signing string, expiry, privacy). It is dense with no obvious filler, though the embedded JSON literal and signing formula make it slightly harder to scan.

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 a mutation tool, the description supplies the signing contract, TTL constraints, expiry behavior, and the visibility guarantee an agent needs to call it correctly. It omits only edge cases such as overwrite/replace semantics for an existing record or failure behavior, which are minor 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 coverage is 100%, so the schema already documents key, sig, and body at a basic level (baseline 3). The description goes beyond it by defining the internal shape of body ({w, tags, ttl}), the tag limits (up to 8 short lowercase tags), the ttl range, and the exact signed-message construction, which the schema does not provide.

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 (publish) and resource (your reachability/presence record) and scopes it to 'those who already know your key' and notes 'It is never listed', which implicitly separates it from the directory-listing siblings like aamio_presence_lookup / aamio_presence_get. An agent can distinguish this tool from its siblings without opening any schema.

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 only implied: the audience phrase 'for those who already know your key' and 'The record expires and must be refreshed' hint at when this tool is relevant. There is no explicit when-to-use/when-not or named alternative (e.g., why use presence_set instead of presence_get or lookup).

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 (readOnly, idempotent, non-destructive, closed world), but the description adds behavior they cannot express: the long-poll semantics of 'wait' returning early on a new message, and that an untouched thread reads empty yet remains waitable. It does not mention rate limits or auth expectations, so it is not a full 5.

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 tight sentences with no filler; the core read-plus-cursor instruction comes first, followed by the blocking behavior and the empty-thread edge case. 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?

With no output schema, the description should hint at the response shape; it references 'the next value from the previous answer' but never states that the answer carries messages plus a next cursor. Otherwise it covers the parameters, blocking behavior, and the empty-thread case adequately for a 4-parameter read tool.

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 100%, so the baseline is 3, but the description adds real meaning beyond the schema: 'after' is a cursor chained from the previous response's 'next' value, and 'wait' causes early return on arrival rather than only elapsing time. That is genuine value over the field 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?

States a specific verb and resource ('Read messages ... using the read key') and pins down the scoping mechanism ('after a sequence number'). It is unambiguous against write-oriented siblings like aamio_send, but it never names or contrasts an alternative tool explicitly.

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 operational guidance: pass the 'next' value from the previous answer as 'after', and use 'wait' to block for arriving messages. It does not state when to prefer this over siblings (e.g. aamio_receipt or aamio_presence_get), so it falls 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 already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description earns credit for adding traits annotations cannot express: the return contents, the absence of message content, and the perishability of the receipt after thread expiry. It stops short of describing the exact return shape or error 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?

Four short sentences, no filler, with the perishability warning front-loaded in the second half where it matters most. The elliptical, fragmentary style ('No content.') is dense but readable.

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 carries the burden of explaining the return value and does so at a conceptual level (hashes, times, signer keys, root). The expiry constraint and the anchoring use case round out what an agent needs; only the literal response format is unspecified, which is a minor gap for a read-only tool.

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?

Both parameters are fully documented in the schema (100% coverage), including the warning not to share the read key. The description adds nothing about 'w' or 'id', so the baseline 3 for high-coverage schemas applies.

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 concretely what the tool produces: hashes, timestamps, signer keys of every message plus a Merkle-style root over them, with 'no content'. That is a specific resource with a clear scope. It does not, however, name or contrast itself with siblings like aamio_read or aamio_close, leaving the agent to infer the distinction.

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 an explicit when-to-use ('if you need proof later', anchor with Verifyum) and a hard precondition/deadline ('take it before the thread expires; afterwards there is nothing to take it from'). No alternative tool is named, but no obvious competitor exists for producing a receipt.

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 that this is a non-idempotent, non-destructive write. The description goes well beyond that: it states the permission model (anyone holding w), the hard 65536-byte payload cap with a large-content workaround, and the exact signing recipe including the signature preimage and the resulting 'verified: true' visible to readers.

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?

Purpose, permission, size limit, and signing are front-loaded and densely packed into a few sentences with no filler. The signing recipe is the longest clause but is justified by being non-obvious protocol detail.

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 a write operation, the description covers the important gaps: authorization, size ceiling, large-payload handling, and signing. It omits what happens on failed permission or whether repeated identical sends duplicate messages (relevant given idempotentHint=false), which keeps it short of a 5.

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 100%, so the baseline is 3. The description earns above that by explaining the relationship between key/sig/w and the canonical signed string, plus that a non-string body is stored as JSON text – semantics the schema patterns alone do not convey.

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 opens with a specific verb+resource: 'Append a message to a thread by its write address.' That is unambiguous and an agent can tell it apart from aamio_read (reading a thread) by the append semantics, though no sibling is named explicitly.

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 an authorization condition ('Anyone with w may do this') and a size-driven routing rule (use a URL and hash above 65536 bytes), which is useful usage context. However, it never states when to prefer this over siblings like aamio_read or aamio_receipt, so usage 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.