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

With no annotations, the description carries the full burden and does it well: it discloses the physical write path, that category is metadata-only, that canonical files are protected from overwrite, frontmatter injection (source: agent + timestamp), and a pgvector indexing side effect. It does not say what error/return occurs if a canonical filename is attempted or whether any permissions are required.

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 primary action, then a tight bulleted list of behavioral constraints, then args. The Args block partly restates names already implied by the schema, a minor redundancy, but every bullet 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?

An output schema exists, so return values need not be explained, and the description thoroughly covers write semantics for an unannotated mutation tool. The remaining gap is failure behavior for the protected canonical-file case and any auth prerequisites.

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% (bare titles only), so the description must compensate — and it does, documenting all three params with format constraints (kebab-case, .md suffix) and concrete examples for both filename and category.

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 (Store) and resource (agent-generated memory entry) plus the exact destination path (vault/memory/). All five siblings are read-only retrieval tools, so this write tool is trivially distinguishable from them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

'agent-generated memory entry' implies the caller context (an agent persisting its own findings), but there is no explicit when-to-use, when-not-to-use, or routing guidance versus alternatives. Usage is inferable 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?

With no annotations, the description carries the full burden and does well: it explicitly states the operation is deterministic, does not perform vector search, and does not dump the vault, which sets clear expectations about scope and safety. However, it doesn't mention the return format beyond "snapshot" or any caching/idempotency guarantees, leaving a small gap for a no-annotation 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?

The description is tightly worded and front-loaded, opening with the primary purpose in the first sentence and qualifying scope in the second. The final sentence partially repeats the "deterministic" qualifier but adds the useful negative constraints, so it mostly 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?

Given the tool has an output schema, the description does not need to enumerate return values, and it focuses appropriately on what is read and what is not done. It is nearly complete for a read-only bootstrap tool, though it could briefly mention the expected read-only/non-mutating nature to align with the absent annotations.

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?

There are zero parameters, so the baseline is 4 per the scoring rules. The description appropriately does not discuss parameters since none exist, and it correctly focuses on behavioral scope instead.

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 (Return) and resource (compact, deterministic bootstrap context snapshot) and enumerates exactly what is read (profile, communication instructions, current goals, active project overviews). This clearly distinguishes it from siblings like lifeos_search and lifeos_read_file by describing a scoped, read-only bootstrap 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?

The description clearly establishes this as a deterministic bootstrap operation that does not perform vector search or dump the vault, implicitly contrasting it with lifeos_search. It gives strong context for when to use it (bootstrap), though it doesn't name a specific alternative tool by name for the non-bootstrap case.

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. 'Retrieve' correctly implies a non-destructive read and it discloses the exact backing file, which is useful behavioral context. It says nothing about what happens if the file is absent or about auth/permissions, so gaps remain for a no-annotation 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 sentence that front-loads the action and resource with zero filler. Nothing to trim.

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 and there are no parameters, so the description needn't explain return values or arguments. The main uncovered case is failure behavior when the referenced file does not exist, which is minor for a simple read.

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 per the baseline there is nothing for the description to clarify. No misleading parameter claims are made.

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 (Retrieve) and resource (the user's explicit personal instructions), and pins down the exact source file identity/how_i_want_ai_to_treat_me.md. That source path distinguishes it from generic siblings like lifeos_read_file, though it doesn't explicitly name the alternatives.

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 statement of when to use this versus lifeos_get_context, lifeos_read_file, or lifeos_search. The intent is inferable from the resource name, but no condition, prerequisite, or alternative is given.

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 carries the full burden. "List" implies a read-only operation and "concise hierarchy" hints at the output structure, but permissions, side effects, and other behavioral traits are not explicitly stated.

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 communicates the scope and output shape with no wasted words.

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, parameterless list tool with an output schema, the description is nearly complete: it states what is listed and implies a hierarchical result. The only minor gap is the lack of explicit behavioral context, but the output schema covers return values.

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 there are no parameter semantics to document. The baseline score for a parameterless tool is 4.

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 ("List") and names the resources ("vault categories and tracked Markdown files"). It is clear what the tool does, but it does not explicitly differentiate itself from sibling tools such as lifeos_search or lifeos_read_file.

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 states what the tool does but provides no guidance on when to use it versus alternatives like lifeos_search or lifeos_get_context. There are no exclusions or usage conditions mentioned.

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 carries the full burden. It usefully discloses that strict path validation prevents directory traversal outside the vault root, which is real behavioral context. However, it says nothing about read-only guarantees, error behavior for missing files, or rate limits.

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 core action, followed by a short security note and a clearly labeled Args section. Efficient overall, though the security sentence sits between the purpose and the argument documentation.

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 values need not be explained. Path format, vault scoping, and traversal safety are covered. Missing only edge-case behavior such as a nonexistent path, which is minor for a single-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 0% and the single parameter is only described as 'Relative Path' in the schema. The description compensates by stating the path is vault-relative and giving concrete format examples ('projects/chronolog.md', 'identity/values.md'), which adds genuine meaning.

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 gives a specific verb ('Read') plus resource ('exact contents of a specific Markdown file from the vault'), which is far more precise than the tool name alone. It does not explicitly contrast with siblings like lifeos_search, but the 'exact contents / specific file' framing implicitly separates it from search-based retrieval.

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 is implied: call this when you already know the vault-relative path of a file. There is no explicit statement of when to prefer lifeos_search or lifeos_get_context instead, and no mention of prerequisites or failure conditions.

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 carries the burden. It does disclose the return shape concretely via the provenance template '[Source: <path> | Heading: <heading> | Similarity: <score>]', which is genuine behavioral context. However it says nothing about indexing state, latency, permissions, or result limits, leaving real gaps for a search 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?

Front-loaded with purpose, then return format, then a compact Args list. Every line earns its place and the reader can stop after the first sentence if only the purpose matters. The bracketed format string is slightly dense but functional.

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 values need not be re-explained, and the description still adds the provenance format. Purpose, all three parameters, and the result shape are covered; only the usage routing against siblings is thin.

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 — and it does, documenting all three parameters: query as natural language, category as an optional filter with concrete example values, and top_k with its default. Only the enumerated category values remain unspecified, keeping this just short of a 5.

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: 'semantic vector search across indexed vault files', which immediately distinguishes it from a literal file read or a memory write. It is clear but never names a sibling (e.g. lifeos_read_file) as an alternative, so the differentiation is left 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?

Usage is only implied by 'semantic vector search' — an agent can infer this is for finding relevant passages by meaning rather than exact path lookup, but there is no explicit when-to-use, when-not-to-use, or named alternative among the siblings. No prerequisites or conditions are stated.

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