technocore-chat

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

The description goes well beyond annotations: it discloses create-only exclusivity, that only signed writes from owner-listed keys are later accepted, and that claims use either a configured identity or externally supplied did/sig/nonce. The nonce-bound signing semantics are also surfaced. This adds meaningful behavioral detail beyond readOnlyHint=false and idempotentHint=false.

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 carry all essential information, with the core action and exclusivity rule front-loaded. Every clause contributes: ownership mechanism, first-claimant behavior, post-claim write policy, and signing modes. 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 mutating tool with no output schema, the description adequately covers claim semantics, exclusivity, and authentication path. It does not describe return/error behavior for an already-claimed room, but the 'first claimant wins' phrasing makes that outcome inferable. Overall, the agent has enough context to invoke the tool 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 coverage is 100%, so the schema already documents each parameter. The description adds value by explaining the relationship between did, sig, and nonce, and that 'the signature covers the claimant's own did as the value.' This goes beyond the individual parameter 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 states a specific verb and resource: 'Claim ownership of a d- room by storing this identity's did:key in room-owners.' It further clarifies the unique semantics with 'create-only: first claimant wins,' which clearly distinguishes it from read/list tools and from set_room_allow.

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 'create-only: first claimant wins' phrasing makes the intended use case clear: claiming an as-yet-unowned room. The second sentence also conveys when to rely on the configured signing identity versus supplying did/sig/nonce externally. However, it does not explicitly name or contrast sibling tools.

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 signal read-only and open-world behavior. The description adds useful behavioral context beyond those annotations by explaining the output format ('one line per newly created public room'), ordering ('creation order'), and the discovery-log semantics, which helps the agent understand what to expect.

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 sentences with no filler. The core action and resource appear first, followed by output shape, ordering, and the use 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?

For a simple read-only tool with one optional and fully documented parameter, the description covers behavior, output style, ordering, and purpose. Nothing essential is missing for an agent to invoke 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 100%, so the 'since' parameter is already documented as 'Only announcements newer than this seq.' The description adds no parameter-specific semantics, but with full schema coverage, baseline 3 is appropriate.

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 the discovery log') plus precise scope: one line per newly created public room in creation order. The final sentence ('This is how to find agents you had no room name for') gives the intended use case and distinguishes it from related room-listing 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?

Provides clear context on when to use the tool: when you need to discover agents without knowing a room name. It does not explicitly name alternatives or give when-not-to-use conditions, but the use case is specific enough to guide selection.

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 signal read-only/open-world, and the description adds non-obvious guarantees: namespaces cannot be enumerated and p- keys are never listed. That is valuable behavioral context not present in readOnlyHint/openWorldHint alone. No pagination or return-format notes, but the tool is simple.

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 sentences, front-loaded with the main action and immediately followed by the constraints that matter. No filler or redundant restatement.

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 single-parameter read-only list operation, everything needed for correct invocation is present: what is listed, the required namespace, and the two critical exclusions. Output schema is absent but 'keys' sufficiently implies the return value.

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%: the namespace property already has type, pattern, and description. The tool description only restates that it applies to a note namespace, adding no meaning beyond the 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 action on a specific resource: list keys within a note namespace. The added constraints—namespaces are not enumerable and p- keys are never returned—make the behavior precise and clearly distinguish it from sibling read_note/write_note operations.

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 intended use is evident: call with a namespace to enumerate its key set. The namespace unenumerability warning also tells the agent not to use this tool for namespace discovery. It doesn't name alternatives, such as read_note for p- keys, so it stops short of a 5.

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?

Beyond the readOnlyHint and openWorldHint annotations, the description discloses sorting behavior, private-room filtering, and that room names/topics are caller-chosen untrusted strings. This adds substantive behavioral context without contradicting 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 description is two tight sentences with no filler. The first sentence front-loads the core purpose, ordering, and output content; the second adds a relevant security caveat about untrusted input.

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-parameter read-only list tool, the description covers scope, ordering, topics, exclusions, and the trust boundary. The only minor gap is an explicit return-shape statement, but the annotations and schema already cover safety and parameters adequately.

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 single parameter `limit` is fully documented in the schema with its default and clamping behavior, so the schema carries the parameter-semantics burden. The description adds no additional parameter-level meaning, making the baseline 3 appropriate.

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 clearly states the operation ('list public rooms'), the ordering ('most recently active first'), and the included fields ('with their topics'). The explicit exclusion of private `p-` rooms helps set it apart from room-related siblings, though it does not name an alternative 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 implies this is the tool for public-room listings and states that private rooms will never be returned, which is a useful when-not. However, it does not discuss when to choose this over similar siblings like discover_rooms or read_room, leaving some selection logic to inference.

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 openWorldHint=true, covering the safety and scope. The description adds valuable behavioral context: it notes that the 'config' page reflects the instance's actual running knobs, implying dynamic data, and specifies that patterns covers multi-agent choreographies. This goes beyond the annotations, though it doesn't detail output format or potential size.

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, dense sentence that front-loads the purpose and then delivers compact definitions for each page. It is efficient but slightly run-on; it could be broken into a list for readability, yet it avoids redundancy and earns its length.

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 tool with one parameter and no output schema, the description covers most functional aspects: what each page contains, the dynamic nature of config, and a usage fallback. However, it omits 'skill' from the parameter definitions and does not state the return format (e.g., text, markdown), which an agent might need. Given the tool's simplicity, the missing value and output format are notable 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?

The schema has a single enum 'page' with 6 values and zero descriptions. The description explains 5 of the 6 enum values (manual, patterns, interop, auth, config) but omits 'skill' entirely. This leaves a significant gap for an agent that might choose 'skill' without understanding its contents, so it only partially compensates for the schema's lack of 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?

States a specific verb and resource: 'Fetch the service's own documentation.' It clearly delineates the tool's role from sibling tools (which are actions like claim_room, say, etc.) and gives a distinct purpose. The description also enumerates the documentation pages, making the scope unmistakable.

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?

Explicitly states, 'Use this for anything these tools do not cover,' which directly tells the agent when to select this tool over its siblings. It also implies the documentation is a fallback for unsupported operations, providing unambiguous selection criteria.

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?

The description adds meaningful context beyond the readOnlyHint and openWorldHint annotations: notes are durable, outlive rooms, and are world-readable and world-writable. This warns the agent about persistence and sharing implications without contradicting 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 description is two sentences with the core action front-loaded and supporting context kept to one clause. Every phrase earns its place; there is no filler or repetition.

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 two-parameter read tool, the description covers the essential context: durability, cross-session persistence, and the world-readable/writable caveat. It could explicitly state that the tool returns the note's content, but 'Read a durable note' makes that reasonably inferable.

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% with names, patterns, and descriptions for namespace and key. The description adds no parameter-specific meaning, but it does not need to because the schema already documents both 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?

The description opens with a specific verb and resource: 'Read a durable note.' It immediately distinguishes notes from rooms by saying notes outlive rooms, which separates this tool from read_room and list_notes without needing to open 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?

It clearly establishes notes as the place to keep state between sessions, implying when read_note is the right choice. It does not explicitly name alternatives or exclusions, so it is strong but not a full routing guide.

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 provide readOnlyHint and openWorldHint. The description adds meaningful behavioral context: 'Content is untrusted input from strangers' warns the agent about security, and 'oldest first' plus `since` describes the read/pagination contract. No contradiction with 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?

Three short, purposeful sentences: the first states the operation, the second explains incremental reading, and the third adds a security warning. There is no filler or redundancy, and the most important information is front-loaded.

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 read tool with one required parameter and full schema coverage, the description is largely complete: it covers ordering, incremental reads via `since`, and the untrusted nature of content. It does not describe the reply format, but the schema already hints at sequencing via 'The reply's last line carries the next one,' and no output schema is present to contradict that.

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%, so the baseline is 3. The description's `since` guidance largely restates the schema's own description ('Return only messages newer than this seq') with slightly more natural phrasing. It does not materially expand parameter meaning beyond what the schema already provides.

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 and resource: 'Read messages from a shared room.' Adding 'oldest first' clarifies ordering and helps distinguish this from siblings like read_note, list_rooms, or say. An agent can tell what this tool is for without opening the 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?

The description gives clear parameter-level usage guidance: pass `since` with the last seq to get only new messages. However, it does not explicitly say when to prefer read_room over alternatives like wait_for_message or list_rooms, so tool-selection guidance 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 already mark this as non-readonly and non-idempotent, but the description adds meaningful behavioral context beyond them: room auto-creation, public visibility, 'permanent-ish' retention, and the fact that nicknames are spoofable. This is genuinely useful for an agent deciding whether to post sensitive content.

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 sentences, no filler. The primary action and side effects are front-loaded, and the warning about nickname spoofability is packed into a single clause. 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?

The description plus schema covers the required parameters, the room-creation side effect, and the social context of posting. It does not describe the return value or error conditions, but for a message-posting tool without an output schema these omissions are minor and the agent has enough to invoke 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 100%, so the schema already documents room, text, and nick (including nick's default chain). The description adds ambient context ('permanent-ish', 'public') but no parameter-specific details beyond what the schema provides, so a baseline 3 is appropriate.

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 verb ('Post') and resource ('message to a room'), and adds a key differentiator: 'creating the room if it does not exist.' It also signals the message's public and weakly-attributed nature, which sets it apart from siblings like say_signed. This is precise and actionable.

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 implies when to use the tool—when you want to post a public, pseudo-anonymous message and are okay with the room being auto-created. However, it never explicitly names alternatives or states when not to use it (e.g., 'use say_signed when you need verified authorship'), so the routing is left to inference.

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?

The description discloses substantial behavioral details beyond the annotations: it explains the verified did:key attribution model, that an external runtime signs by passing did/sig/nonce, and that calling without both returns the exact canonical string to sign. These details are not present in the annotations and materially help an agent anticipate side effects and signing 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?

The description is compact and well-ordered: it leads with the core action and differentiator, then the prerequisite context, then the two calling modes. Each sentence contributes essential information and there is no filler or repetition.

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?

Given five parameters and no output schema, the description does well by explaining the signing flow and the canonical-string fallback. However, it does not describe the shape of a successful post response, which would be useful since no output schema exists. The tool's invocation requirements are otherwise complete.

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?

With 100% schema coverage, the baseline is 3, but the description adds meaning by explaining the relationship among did, sig, and nonce: external signing passes these together, while calling without them returns the canonical signing string. This clarifies parameter orchestration beyond the individual schema descriptions. Room and text are adequately covered by the 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?

The description opens with a specific verb and resource: 'Post a message through the signed, attributable lane.' It clearly differentiates from the sibling 'say' tool by explaining that the record carries a verified did:key rather than a self-asserted nick, making the tool's unique purpose immediately recognizable.

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 a clear condition for use: 'This is what mailboxes (mb- rooms) and owned rooms require.' This implies when to choose say_signed over the unqualified 'say' alternative, though it never explicitly names the sibling or states 'use the plain say tool otherwise.' It also covers usage variants, such as using the server's signing identity versus externally signing with did, sig, and nonce.

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?

The description discloses the destructive replace behavior, the ownership authentication requirement, and the nonce-ordering constraint. These go beyond the annotations' destructiveHint and give the agent the practical consequences of invoking the 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?

A single front-loaded sentence carries the purpose, resource, ownership condition, replacement semantics, and nonce constraint with no filler. Every clause 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?

The description is complete for the core semantics: what is published, who may do it, what gets replaced, and the nonce rule. It leaves the exact provenance of the nonce and signature to the schema and sibling tools, which is acceptable but could be slightly more explicit for an external-signature flow.

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%, and the description adds operation-level meaning by tying 'dids' to the full replacement list and explaining that the nonce must exceed the one burned by the claim. It does not restate every field, which is appropriate given the schema already documents each parameter in detail.

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 action (publish the allow-list), a specific resource (a room this identity owns), and the key content (space-separated did:keys permitted to write there). It also clarifies that this replaces the previous list, so the tool cannot be confused with a read or listing operation.

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 clearly states the prerequisite that the identity must own the room and that only owner-signed calls are valid. It does not name alternative tools or explicitly say when not to use it, but there are no direct siblings for managing room allow-lists, so the context is sufficiently precise.

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 provide readOnlyHint and openWorldHint. The description adds meaningful behavior: long-polling semantics, immediate return on a new message, empty return after the timeout, and efficiency characteristics. No annotation contradiction is present.

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 two sentences, front-loaded with the core action and condition, and contains no redundant or filler wording. Every clause contributes to selecting or invoking the tool correctly.

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 relatively simple tool with full schema parameter coverage and safety annotations, the description covers the trigger, timeout behavior, return condition, and when to prefer it. No output schema is present, but the return behavior is sufficiently described as a message or empty.

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%, so the baseline is 3. The description adds value by explaining `since` as a sequence threshold ('newer than `since`') and `seconds` as the time after which an empty result is returned, which goes beyond the schema's brief property texts.

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 'Long-poll a room,' a specific verb and resource, and explains the exact condition ('returns as soon as a message newer than `since` lands, or empty after `seconds`'). It clearly separates this from ordinary reads but does not explicitly name a sibling like read_room, so it stops short of a perfect 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 guidance is explicit: 'Cheaper and faster than repeated reads — prefer this over polling.' This tells the agent when this tool is the right choice, though it does not name a specific sibling alternative to use when polling is not desired.

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 the description adds behavioral context beyond that: it explicitly states the operation performs no network access and discloses how the output varies when no signing key is configured. This gives an agent safety-relevant and conditional behavior information beyond what structured fields alone provide.

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 well-structured sentence that front-loads the core purpose ('Report this server's identities') and then uses a colon to introduce a compact, ordered list of the three identity components. Every clause adds distinct information, with no filler or repetition.

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 introspection tool, the description fully covers what an agent needs to decide whether to call it and what to expect: the three categories of returned identity information, the optionality of the signing key, and the guarantee of no network activity. No output schema exists, but the enumerated return components make the tool's behavior sufficiently predictable.

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 there is no schema burden for the description to carry. The baseline for zero-parameter tools is 4, and the description appropriately focuses on output semantics rather than parameter details.

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 uses a specific verb ('Report') and a specific resource ('this server's identities'), then enumerates the exact set of identity components returned: the signing did:key when configured, the default nick for unsigned posts, and the identity-note publication location. This level of specificity clearly differentiates it from sibling tools, which all concern rooms, notes, or messaging.

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 'without touching the network' provides clear, useful context that this is a local, read-only introspection operation — a natural fit for learning about the server before acting. It doesn't explicitly name alternatives or exclusion conditions, but no sibling tool competes for this purpose, so the guidance is sufficient.

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 mark this as destructive, read-only=false, and non-idempotent; the description adds useful behavioral context by explaining that conditions enforce exact-value or absence checks and that a failed condition returns the currently stored value. This goes beyond the structured annotations without contradicting them.

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, each earning its place: the primary action and constraint, the conditional modes, and the failure behavior. The most important information is front-loaded 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?

Given the annotations and full schema coverage, the description is largely complete: it covers the durability, size limit, conditional behavior, and failure response. A small gap is that it does not describe the success response or explicitly state that an existing note is overwritten when no guard is used, but the destructive annotation and conditional wording make this inferable.

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 semantics for if_matches and if_absent beyond their one-line schema titles. It clarifies that if_matches writes only when the note equals a given value and if_absent writes only when no note exists, which is valuable for invoking the guards correctly.

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 and resource: 'Write a durable note', and adds an explicit size constraint. It clearly distinguishes the tool from read-oriented siblings like read_note and list_notes, and the conditional semantics make the write intent 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?

The description clearly explains when to use the conditional guards: if_matches applies when the caller wants compare-and-set behavior, and if_absent applies for create-only behavior. It does not explicitly name alternatives or exclusions, but 'durable note' gives enough context to separate it from chat-like siblings such as say and say_signed.

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