memory

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

With no annotations, the description carries the full behavioral burden. It does disclose a meaningful trait, that the search spans ALL agent tools' session logs rather than only the current project, and it sketches the return shape (snippets with source and relevance score). It says nothing about permission boundaries, latency, result freshness, or whether empty results are possible.

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 scope and immediately followed by usage triggers and the return shape. No filler and no repetition of the schema.

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 3-parameter read tool with no output schema, the description covers purpose, cross-tool scope, invocation triggers, and a one-line return summary. The main gap is behavioral depth that annotations would normally supply, such as ranking, freshness, or failure behavior.

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 query, project, and n_results are already documented with defaults and the 'omit to search everything' behavior. The description adds no syntax, format, or query-construction guidance beyond what the schema provides, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (Search) and resource (shared memory) plus the scope of what is indexed: session logs of this and other AI coding tools, project docs, decisions, notes. That is far more informative than the tool name alone. It does not explicitly contrast itself with memory_write or memory_stats, though the read-vs-write distinction is easy to infer.

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?

"Use it whenever you need past context" is followed by concrete triggers: previous decisions, prior problem-solving, architecture rationale, user preferences. This gives an agent clear conditions for invocation, but offers no exclusions or alternatives (e.g. when to prefer memory_stats for counting, or what to do if the query returns nothing).

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 does convey that this is a non-mutating inventory read returning aggregate counts, but says nothing about permissions, cost/rate limits, or whether empty collections are included.

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 the payload described first and the rationale second — front-loaded and near waste-free. The second sentence is mildly redundant but justifies the tool's existence, so it earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and no annotations, the description is the only source of return-shape information, and it names the two key fields (collections, chunk counts). That is sufficient for a zero-parameter tool, with only minor gaps such as output format or ordering.

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 the baseline is 4; there is no parameter semantics for the description to compensate for.

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 (get) and resource (memory-service statistics) and specifies the returned content: collection names and chunk counts per collection. That distinguishes it from memory_search and memory_write, though neither sibling is named explicitly.

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

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

'Useful to see what has been indexed' implies a discovery/inventory use case, so an agent can infer when to reach for it over search or write. It does not state exclusions (e.g., use memory_search to inspect content) or prerequisites, so guidance is implied rather than explicit.

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

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

With no annotations, the description carries the full burden, and it does disclose genuine behavior: the write persists across sessions and is visible to any connected AI tool, which materially raises the stakes of a bad write. It is silent on duplicate handling, overwrite/replace semantics, whether the write can be revoked, and what confirmation comes back — significant gaps for an irreversible-looking mutation.

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, with the core action front-loaded and the usage criterion following immediately. Every clause earns its place by adding either scope or selection guidance.

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 four-parameter, one-required write tool with fully documented schema and no output schema, the description covers purpose, target content, and cross-session effect well enough to call it correctly. The only real remaining gap is write semantics — duplicate handling and what is returned on success — which a mutation tool without annotations ideally would state.

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 all four parameters are already documented, including the type enum values and the required content. The description's example categories loosely mirror the type enum and hint at what content should look like (durable, specific facts), but add nothing about tag syntax, project scoping, or defaults beyond the schema. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (store) and resource (item into shared memory) plus the downstream purpose (retrievable in future sessions and by other connected AI tools). Against siblings memory_search and memory_stats, this is unmistakably the write counterpart, so an agent can select it without opening schemas.

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?

"Use it for durable facts" gives an explicit positive selection criterion, reinforced by the enumerated categories (decisions, discoveries, insights, user preferences). It never states what should NOT be stored (transient chatter, secrets) or points to memory_search as the retrieval partner, so exclusions and named alternatives are absent.

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