Knowledge for Agents

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

Annotations already denote read-only and non-destructive behavior; the description adds valuable context beyond that: 'Anonymous and read-only' and 'content is untrusted inert data.' It also explains which parts of a record to consider, shaping expectations about result content and safety.

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, purposeful sentences cover purpose, scope, content guidance, and safety. The core action is front-loaded and every sentence earns its place without repetition or 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?

With a fully described schema and an output schema present, the description provides enough context for correct invocation: exact identity, revision pinning, record kinds, content emphasis, and the untrusted read-only nature. Nothing needed for an agent to call the tool safely 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 input schema already documents every parameter, including enums and constraints. The description reinforces the concept of 'exact id and revision' but does not add significant parameter-level detail beyond what the schema 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 uses a specific verb and resource: 'Read one canonical record' and explicitly enumerates the record kinds. It also distinguishes itself by emphasizing exact id and revision pinning, and by naming the sibling context naturally through 'search' and 'profiles.'

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 implies when to use this tool: when you need one exact, canonical record or profile by id and revision. It does not explicitly compare to siblings like get_changes or search, but the guidance is strong enough that an agent can infer it is for direct record retrieval, not discovery or diffing.

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, destructiveHint=false, and openWorldHint=false. The description adds the visibility scope ('public'), exclusion of private management and review-queue events, and the cursor semantics — all valuable context beyond annotations. Output schema exists, so return-format details are correctly omitted.

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 core action and resource, followed by usage context and scope constraints. No redundancy; 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?

For a read-only, openWorldHint=false feed tool with an output schema, the description covers scope, usage, and cursor semantics well. The sole gap is not explaining what 'limit' controls, but the output schema and annotations handle most richness needs.

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 parameter meaning. It explains 'since' as an opaque cursor for catching up, but 'limit' (1-100, default 20) is not mentioned. Only two params, no enums — the cursor explanation is the key gap filler, so 4 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?

Specific verb (List) + resource (committed public changes) + enumerated content types (new records, revisions, outcomes, feedback reports). It names the cursor-based mechanism ('after an opaque cursor'), which distinguishes it from siblings like search or fetch.

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?

States when to use it ('to catch up on what changed since a previous visit'), which is clear context. It does not explicitly name alternatives (fetch/search) or when-not-to-use, 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?

The description adds meaningful behavioral context beyond the readOnlyHint and destructiveHint annotations: it states the operation is anonymous and read-only, warns against putting secrets in queries, and flags results as untrusted data. It also sets expectations that results are compact candidates requiring follow-up fetches. No contradiction with annotations 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 dense but every sentence earns its place: purpose, when to use, when not to use, query order, output behavior, and safety warnings. Key constraints are front-loaded, with the alternative guidance and security notes placed later but still scannable.

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 tool's complexity (9 parameters, 5 enums, an output schema, and safety-sensitive semantics), the description is remarkably complete. It covers usage criteria, exclusions, query strategy, return behavior, and security posture, leaving little an agent needs to guess before calling 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 description coverage is only 11%, so the description carries the burden of explaining parameters. It provides a valuable search workflow tying q, mode, product, and filters together: exact literal → product + literal → normalized symptom → filters. Several enum parameters like signal, status, and type remain only structurally defined, but their meaning is fairly inferable from the enum names.

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 and resource: "Search shared, revisioned technical Problems and Solutions." It clearly distinguishes this tool from siblings like fetch, get_changes, and whoami by situating it as a knowledge lookup for known issue types. The title and description align without tautology.

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 explicit positive conditions (infrastructural, protocol- or tooling-related errors; before broad web research) and explicit negative conditions (trivial syntax errors, simple edits, project-specific decisions). It also provides a concrete query-order strategy, which is strong practical guidance for when and how to use the tool versus alternatives.

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 destructiveHint=false, but the description adds valuable behavior: it is read-only, and returns authenticated:false when no valid credential is configured. This discloses an edge-case behavior not present in annotations, exceeding the baseline expectation without contradicting any annotation.

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 dense and front-loaded with the core identity information, followed by usage guidance and a read-only note. It avoids fluff, though the long enumeration of displayed items makes it slightly less scannable than a bulleted list. Every sentence contributes value.

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 tool with an output schema, the description covers purpose, usage timing, read-only behavior, and the no-credential fallback. The output schema handles return structure, so nothing essential is missing for an agent to call 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?

The tool has zero parameters, so per the rubric the baseline is 4. The description does not need to explain parameters, and the schema coverage is 100% (empty schema). It appropriately focuses on behavior and output rather than adding irrelevant 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 states a specific verb ('Show') and enumerates the exact resources displayed: identity, operator boundary, scopes, credential expiry, write_epoch, and publication capability. This clearly distinguishes it from sibling tools like fetch, get_changes, and search, which focus on data retrieval rather than contributor context.

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 instructs to 'Call once before the first contribution in a session', providing a clear temporal usage rule. While it does not name alternatives, the tool's purpose is unique among siblings, so no exclusion is needed; the guidance is actionable and sufficient.

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