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

No annotations, so the description carries the full burden, and it delivers real behavioral detail: chunking by headings and the exact title-derivation rule (first H1, else filename). It omits permission/auth requirements and what happens on conflicts with existing memory, which are notable for a write 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?

Three sentences, each doing distinct work: purpose, chunking/title rule, invocation gate. Front-loaded with the action and free of 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?

An output schema exists, so return values need not be explained, and the description covers the key ingestion behavior and the calling gate. Minor gap: consequences of adding a duplicate or invalid file are unstated.

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 'path', 'project', and 'tags' are already documented in the schema. The description only indirectly reinforces that the path is a local markdown file; it adds no syntax or constraint detail beyond the schema, matching the baseline 3.

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 concrete verb and resource ('Ajoute un fichier markdown local à la mémoire') and adds the chunking semantic ('découpé par titres'). The local-markdown resource implicitly distinguishes it from add_text/add_url, but no sibling is named explicitly, so it stops short of a 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?

Gives an unambiguous gating rule: call ONLY when Denis explicitly requests it in the current message, never on the agent's own initiative. This is explicit when/when-not guidance, the strongest form of routing instruction.

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 behavioral burden. It discloses the important trigger constraint (must be explicitly requested), which is real added value, but says nothing about persistence scope, duplicate handling, required permissions, or whether writes are reversible for a mutation 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?

Two short sentences with no filler; the purpose comes first and the invocation constraint follows immediately. 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?

An output schema exists, so return values need not be described, and all four parameters are fully documented in the schema. What remains thin is context about the target memory store and whether a valid 'project' must already exist, but the definition is otherwise sufficient to invoke 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 tags, text, title, and project. The description adds no parameter-level meaning beyond what the schema provides, which is the baseline 3 case.

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 ('Ajoute un texte brut à la mémoire'), and the qualifier 'texte brut' implicitly separates it from add_url and add_file. It stops short of naming those siblings, so differentiation is inferable rather than explicit.

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?

Gives a clear, strong usage condition: call only when Denis explicitly requests it in the current message, never on the agent's own initiative. It does not name an alternative tool or the reverse condition (e.g. when to prefer add_url/add_file), so it stays at a solid 4 rather than a full when/when-not/alternatives statement.

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 and does disclose useful traits: it downloads, extracts main content, and derives the title from the page. However, it says nothing about failure modes (unreachable/blocked URLs), permissions, deduplication, or rate limits, leaving meaningful gaps for a mutation 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?

Three short sentences, front-loaded with the purpose before the usage restriction. No filler; every sentence carries either behavior or a constraint.

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 described, and the description covers purpose, internal behavior, and usage conditions. It is nearly complete, with only edge-case handling left unstated.

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 url, tags, and project are already documented in the schema. The description adds no parameter-level detail such as URL format expectations beyond http(s) or how tags/project affect storage, so the 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?

The description names a specific multi-step operation: download a web page, extract its main content, and add it to memory, with the title taken from the page. This clearly separates it from add_text and add_file siblings, though it doesn't explicitly name those alternatives by name.

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 and unusually strong usage constraint: call ONLY if Denis explicitly asks in his current message, never on your own initiative. This is a clear when/when-not rule, but it does not point to a concrete alternative tool for the cases where you shouldn't use this one.

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 destructiveHint=true, but the description adds real value beyond them: it discloses that the deletion is permanent ('définitivement'), that it cascades to chunks, and that a summary of what was removed is returned. It does not mention permission or auth requirements, so not a full 5.

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 load-bearing: what is deleted, what is returned, and the invocation constraint. The restriction is front-loaded after the core purpose with 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?

An output schema exists so return detail is covered, annotations cover the destructive profile, and the description adds cascade behavior plus the consent constraint. An agent has everything needed to decide and call 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% for the single doc_id parameter, and the description adds no meaning beyond it (no format hints, no alternative identification schemes). Baseline 3 is appropriate when the schema fully documents the only parameter.

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 (supprime) and resource (document), plus the cascade scope (et ses chunks), which distinguishes it from siblings like update or add_text. The 'définitivement' qualifier makes the permanence 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?

Gives an explicit, unusually strict invocation condition: only when the user explicitly requests it in the current message, never on the agent's own initiative. This is exactly the when/when-not guidance that prevents accidental destructive calls.

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?

readOnlyHint=true already tells the agent this is a safe read operation, and the description's mention of returned full text plus metadata is largely restated by the existing output schema. It adds little beyond the structured fields, e.g. no note on missing-document behavior or permissions.

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 short sentence with no filler, front-loading the resource. It is efficient, though extremely terse for a tool whose name is as generic as 'get'.

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 an output schema covering return values and annotations covering the safety profile, the description only needs to state scope, which it does. Minor gap: nothing about failures for unknown doc_id or the relationship to the sibling search/list tools.

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% for the single parameter, and its schema text ('Identifiant renvoyé par search') already explains provenance. The description contributes no additional parameter meaning, so 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?

The description states a specific retrieval action and resource ('texte intégral d'un document de la mémoire, avec ses métadonnées'), which is far clearer than the bare name 'get'. It implicitly contrasts with list/search by emphasizing full-text retrieval of a single document, though it never names those siblings 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?

No explicit when-to-use statement or exclusion versus search, list_docs, or the add_* tools. The only usage signal is indirect, via the param note 'Identifiant renvoyé par search', which implies a search-then-fetch flow but leaves the agent to infer it.

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, so safety is covered. The description adds useful context that results are metadata-only without document text and that ordering is newest-first, which goes beyond the annotations, but no pagination or result-count behavior is described.

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, tight sentence with the ordering constraint front-loaded and zero filler. Appropriately sized, though it is the bare minimum for a tool with an undocumented parameter.

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 needn't be explained, and the metadata/text distinction is a helpful addition. However, for only two parameters the description omits the 'n' limit entirely, leaving a genuine gap.

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 only 50%: 'n' has no description in either schema or description, and the description never mentions the result-count limit (max 50, default 20). Only 'project' is documented in the schema, so the description fails to compensate for the coverage gap.

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+resource ('list documents') plus sort order (most recent first) and content scope (metadata only, no text). Clear purpose, but there is no differentiation from the sibling 'search' tool or explanation of how it differs.

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 on when to use this versus 'search' or 'projects'. The listing intent is implied by the name, but no conditions, exclusions, or alternatives are 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?

The readOnlyHint annotation already tells the agent this is a safe non-mutating call, so the description need not restate that. It does add the useful fact that each entry carries a document count, implying a small summary payload rather than full content. It does not disclose ordering or whether projects with zero documents 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 no filler; the resource and its distinguishing content come first and the selection guidance second. Only quibble is the slight terseness of the first sentence, which omits a verb.

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 the description is not obliged to describe return values, and it only needs to convey scope and intent. For a zero-parameter enumeration tool this is close to sufficient; only ordering/pagination behavior is unstated.

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 no parameters, so per the rubric the baseline is 4. The description's mention of the `project` filter is about a sibling tool (search), not this one, so it adds no parameter meaning here and cannot exceed the baseline.

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 concrete resource (projects held in memory) plus the payload (document count per project), which is more than a restatement of the name 'Projects'. It is distinguishable from the generic siblings (get, delete, search, list_docs) by virtue of being a zero-argument enumeration with counts. It lacks an explicit verb, but the intent is 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?

Explicitly gives the use case: consult this to pick the `project` filter value for search. That routes the agent to the right sibling at the right moment. It stops short of the full 5 because it gives no when-not guidance (e.g. that it should not be used to retrieve document content).

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?

readOnlyHint=true already covers the safety profile. Beyond that, the description discloses the retrieval mechanism (hybrid dense+sparse with reranking) and the shape of the result (short excerpts with doc_id, titre, projet, score), which genuinely helps an agent reason about result quality and next steps.

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 tight sentences: purpose and mechanism first, then the call-timing guidance, then the return shape and the routing hint. No filler, and the most decision-relevant 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?

With an output schema present, return values need not be spelled out, and the brief mention of excerpt fields is a bonus. Combined with the retrieval mechanism and the `get` handoff, an agent has enough to call it correctly; only filtering behavior across the sibling tools is left implicit.

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 `k`, `tags`, `project` and `query` are all documented in the input schema itself. The description adds no extra semantics about these parameters, so the 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+resource with mechanism: hybrid (dense + sparse, reranking) search over Denis's memory, and explicitly distinguishes itself from the sibling `get` (excerpts vs. full document). An agent can tell what it is 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?

"À appeler avant de répondre sur ses projets, décisions ou notes" gives a clear trigger context, and it names `get` as the alternative for reading a whole document. However, it gives no exclusions — e.g., nothing says to use `list_docs` or `projects` for enumeration instead.

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 only carry idempotentHint=true, so the description adds meaningful disclosure beyond them: what is preserved (doc_id, title, project, tags), that the text is fully replaced, and the side effect that chunks are reindexed. It stops short of noting permissions or failure modes, but the behavioral picture is substantially richer than the 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?

Two tightly packed sentences with zero waste: the first states scope and preservation/reindexing behavior, the second states the calling precondition. Front-loaded 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?

For a two-parameter mutation tool that ships an output schema, everything an agent needs is present: replacement semantics, preserved fields, the reindexing side effect, and a strict invocation rule. Nothing material 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 description coverage is 100% with only two parameters, so the schema already documents both text and doc_id. The description adds only a light constraint ('même doc_id', existing document) without new format or syntax detail, so the 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 and resource ('Remplace le texte d'un document existant') and clarifies that it acts on an existing doc_id while preserving title, project and tags, which distinguishes it from the add_* siblings that add new content. An agent can tell it replaces the whole text rather than appending.

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?

Explicit and strict: 'N'appeler QUE si Denis le demande explicitement dans son message courant ; jamais de ta propre initiative.' This gives a clear when-to-use condition and an explicit prohibition, leaving nothing to inference.

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