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

No annotations are provided, so the description carries the burden of behavioral disclosure. It adds that the invariants are 'verified' and that the call is mandatory before sensitive changes, but it does not state whether the tool is read-only, whether it enforces anything, or what happens if invariants are violated.

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 terse sentences with no filler. It front-loads the core definition and then states the mandatory usage context, making it highly scannable and 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?

The description provides essential usage context and examples, and an output schema exists to cover return values. However, with no annotations and no schema-level parameter descriptions, the project parameter remains ambiguous and the tool's behavioral profile is incompletely specified.

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 compensate. The examples give some semantics for 'domain' and 'operation', but the optional 'project' parameter is left completely unexplained, and valid values are not enumerated.

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 that the tool returns verified invariants for a domain operation and gives concrete examples ('wallet' / 'reverse transaction'). This clearly differentiates it from sibling tools like get_recent_work or get_project_overview, though it does not explicitly name an alternative.

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 this is MANDATORY before money-path/auth/tenancy changes, providing a clear trigger condition. It does not mention when not to use it or point to alternative tools, 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?

No annotations are provided, so the description bears the full burden. It discloses neither safety/side effects nor output format, authentication, pagination, or data volume. The 'get' name implies read-only behavior, but the description itself doesn't confirm this or any limitations.

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 no filler. The content list is front-loaded, and the usage trigger is stated separately. 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 2-parameter read tool, the description is reasonably complete, but it doesn't define parameter semantics or distinguish itself from overlapping sibling tools. With no output schema and no annotations, an agent is left to guess the exact call shape and return style.

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%, and the schema only provides parameter titles. The description's phrase 'a project/repository' touches on the domain but does not explain the distinction between 'project' and 'repository', their optionality, or behavior when 'repository' is null.

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 ('project/repository') and enumerates the deliverable contents ('Product purpose, service map, boundaries, and critical rules'), which clearly distinguishes it from sibling tools. It lacks an explicit retrieval verb, but the tool name plus content list make the action clear.

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 trigger: 'Call when entering a repo for the first time.' This is clear context but doesn't mention when not to use it or contrast it with overlapping siblings like get_domain_rules or read_memory.

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 no annotations, the description carries the full burden. It discloses the result content and sort order, and hints that 'since' is an ISO date, but it does not explain that 'since' filters entries or describe the effect of omitting it. The read-only nature is implied by the verb 'get' but not made explicit.

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 definition is short and front-loaded with the core purpose, with no filler. The 'since = ISO date' note is terse but acceptable, so it loses a point only for being cryptic rather than explanatory.

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?

An output schema exists, so return-value documentation is not required. However, the description fails to document the 'project' parameter and does not clarify what 'since' actually does. For a two-parameter read tool this is an incomplete guide.

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 compensate for both parameters. It only covers 'since' with a format hint (ISO date) but not its filtering semantics, and it omits the 'project' parameter entirely.

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 identifies the resource (worklog), the content ('what was done and why'), and the ordering ('newest first'). It distinguishes itself as a worklog tool among memory/decision siblings, though it does not name a contrasting 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?

No guidance is provided on when to use this tool versus the sibling tools. There are no alternatives named and no exclusions stated, so an agent must guess when a worklog lookup is appropriate.

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 are entirely absent, so the description carries the full burden of behavioral disclosure. It only says what is returned, not how retrieval works, whether the operation is read-only, what 'relevant' means, or whether there are side effects or access implications.

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 sentence with no filler and front-loads the core noun phrase. It is appropriately terse, though the ADR acronym is unexplained and 'paths it touches' is somewhat ambiguous.

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 tool has an output schema, which partially covers return-value expectations, but the description lacks behavioral, usage, and parameter-interpretation context. With no annotations and only a minimal description, an agent would need to infer important details about when and how to call this 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?

The schema provides 0% description coverage, so the description must compensate; it partially does by mapping 'a task' to the task parameter and 'paths it touches' to the paths parameter. It adds useful top-level semantics but does not explain parameter format, optionality behavior, or how the two parameters interact.

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 delivered resource (ADRs and past decisions) and the relevance scope (task or paths it touches), making the tool's basic function clear beyond the tool name. It doesn't explicitly contrast with sibling tools, but the specific 'ADRs/past decisions' focus is reasonably distinct.

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 guidance on when to use this tool versus alternatives like get_task_context, read_memory, or get_domain_rules. The phrase 'relevant to a task or paths' implies a use context, but it does not state exclusions, preconditions, or what distinguishes this tool from similar memory/retrieval 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?

With no annotations provided, the description carries the behavioral disclosure burden. It usefully reveals what the returned packet contains and that it should precede planning, but it does not explicitly state whether the operation is read-only, whether it has side effects, or what permissions/inputs beyond the obvious are needed. Some transparency is present, but the safety profile is left implicit.

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 compact sentence with a colon-delimited list of contents followed by a direct, imperative usage rule. It is front-loaded, scannable, and contains no filler or redundant restatement of the tool name.

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 presence of an output schema, the description does not need to explain return values, and it covers the main high-level contents and invocation timing well. It is slightly incomplete in that it omits guidance on optional scoping parameters and sibling-tool differentiation, but it is adequate for a task-context retrieval 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 0%, and the description provides no parameter-level guidance. The field names (task, paths, project, repository, incident_id) are partially self-explanatory, and 'task-specific' aligns with the required 'task' parameter, but the description does not clarify how optional parameters interact, which combinations are valid, or what values are expected. In a low-coverage situation, the description should compensate and does not.

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 identifies a specific resource—a task-specific packet—and enumerates its contents (architecture, business rules, gotchas, code pointers, risks, verification steps), which makes the tool's purpose fairly clear. It stops short of a strong action verb like 'retrieve' or 'build', but the intent is unambiguous and distinct from broader sibling tools like get_project_overview.

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 explicit 'Call BEFORE planning' gives clear temporal guidance, telling an agent when in the workflow this tool should be invoked. It does not explicitly compare against alternatives or state when not to use the tool, but the timing guidance is strong enough for a 4.

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 no annotations present, the description carries the full burden and it delivers: it discloses auto-approval default, the PM_REVIEW=1 escape hatch, that redaction/collision-safety are NOT relaxed, that secrets are stripped because the store is committed to git, that id clashes suffix rather than overwrite, and that auto-approved entries carry verified_by='auto'. It also warns against credentials — comprehensive side-effect disclosure well beyond the minimum.

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 dense paragraphs, front-loaded with the action and the one flag (PM_REVIEW=1) an agent must know first; the rationale sentence explains why auto-approve is the default, which prevents the agent from second-guessing the contract. Minor redundancy exists ('committed to git' appears twice) and the middle rationale paragraph could be tightened, but no sentence 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?

For a 10-parameter write tool with no annotations and no output schema, the description covers the essential ground: purpose, approval behavior, safety constraints, usage recipes, and the required refs/content formats. The gaps are the unexplained parameters (symbol, source, file, repository, tags) and the absence of any statement about return values or success signals, though the behavioral contract is unusually 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?

Schema coverage is 0%, so the description must compensate — and it does for the high-stakes parameters: type is given concrete values ('code_symbol', 'worklog'), refs is explained as PRD/spec/ticket references, and content gets a full WHAT/WHY/NEED/WHY THIS WAY/GOTCHA template. However, symbol, source, file, repository, and tags get no semantic explanation, leaving ambiguity around the symbol/file/repository distinction.

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?

Opens with 'Record a new memory' — a specific verb plus resource — and immediately extends into the behavioral contract (auto-approved by default, PM_REVIEW=1 queue). All eight siblings are read/query tools (get_, search_, read_, why_), so the write verb clearly separates this tool; the concrete use cases (code_symbol per function, worklog entry, 'why does X work this way?' answers) make the purpose 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?

The third paragraph is a direct usage instruction: 'Use at task completion' with a precise recipe — one type='code_symbol' entry per changed function, the WHAT/WHY/NEED/WHY THIS WAY/GOTCHA body format, refs pointing at PRD/spec/ticket, plus a worklog entry — and a second trigger ('record the answer when the user asks why does X work this way?'). It doesn't name read-sibling alternatives explicitly, but the write-vs-read split plus the concrete triggers make when-to-use unambiguous.

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 no annotations, the description carries the full behavioral burden. It clearly discloses that this returns the full note rather than a snippet, and that it returns None for unknown/stale ids instead of guessing a nearest match. This is precise and honest behavioral disclosure.

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 behavior, the relationship to search, and the edge-case return 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?

The tool is simple, has one parameter, and has an output schema. The description covers the source of the id, the return behavior, and the stale-id edge case, 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 schema only provides a string type and parameter name, so the description must compensate. It does so by explaining that memory_id is specifically the id a search hit returned, and that stale ids from older sessions are possible. This adds essential meaning not present in 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 states a specific verb and resource: it reads the FULL body of one memory by id. It also distinguishes itself from search_product_memory by positioning itself as the counterpart to snippet results.

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 to use this tool after search has returned a hit and enough context to choose, then calls out that this retrieves the whole note. It names the alternative workflow (search gives the passage) and the correct sequencing.

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 no annotations, the description carries the burden and does well: it states the tool returns snippets plus `store_path`, explains the cost tradeoff of `full=True` ('costs roughly five times as much'), and implies read-only behavior through 'search' and 'returns.' It does not detail rate limits or authorization, but for a search tool the key behavioral aspects (output format, performance) are covered.

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 (about 60 words), front-loaded with the core purpose, and each subsequent sentence adds vital operational detail (return format, follow-up action, cost tradeoff). There is no filler or repeated schema information.

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?

Despite the lack of parameter descriptions and annotations, the description covers the essential agent workflow: search by query, inspect snippets, read a file when relevant, or request full bodies at a known cost. The presence of an output schema excuses deeper return-value detail, but the intended meaning of project/repository filters remains under-specified.

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 compensate. It explains the `full` parameter meaningfully (snippets vs. whole bodies, cost), but `query`, `limit`, `project`, and `repository` receive no elaboration—their meanings are left to inference from names and types. The description adds some semantic value but leaves significant gaps for filtering 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 'Ranked search over all verified product/architecture/incident memory,' naming a specific verb (search), a distinct resource (verified memory), and a clear scope. This differentiates it from siblings like read_memory (which reads files by path rather than searching content) without needing to reference them 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?

The description gives actionable workflow guidance: 'Read the file when a snippet turns out to be the thing' and explains when to use `full=True` versus scanning snippets. This effectively contrasts the tool with file-read alternatives, though it does not explicitly discuss when to prefer search_product_memory over other sibling search-like tools such as get_related_decisions.

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 no annotations, the description carries the full burden. It communicates an informational purpose and implies a safe read-only operation, but it does not explicitly state that it has no side effects, what happens when no card exists, or any permission requirements.

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 front-loaded sentence that wastes no words. It packs the tool's purpose, output type, and usage timing into a compact, readable form.

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 only two parameters, an output schema, and a clear usage directive, the description is largely complete for invocation. The main gap is not explaining how it differs from closely related siblings like get_related_decisions, but that is not required for a correct call.

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 0%, so the description must compensate. 'Function or file' loosely maps to the `file` and optional `symbol` parameters, but the description never explicitly connects those concepts to the parameter names or explains the optional/nullable behavior of `symbol`.

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 identifies the tool as a 'WHAT/WHY/WHY-THIS-WAY/GOTCHA card' for a function or file, with the explicit purpose of surfacing past decisions before rewriting. This distinguishes it from sibling retrieval tools like read_memory or get_project_overview by anchoring it to code-specific rationale.

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 explicitly states when to call: 'before rewriting existing code.' It does not list exclusions or name alternative sibling tools, but the when-to-use guidance is clear and actionable.

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