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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuinely non-obvious behavior beyond that: the response is mode-dependent — in demo mode it also returns this session's access log. What's still missing is any hint about what the permission set looks like or how failures behave, but for a zero-parameter read tool this is solid added context.

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 capability front-loaded and the conditional demo-mode behavior second. The opening clause is slightly awkwardly phrased as a noun phrase rather than a verb phrase, which is the only structural weakness.

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 parameters, the description carries the return-value burden and does reasonably well: it says the result covers permissions, the full-entry-text flag, and demo-mode access log. It could go one step further by noting the shape or that the call always succeeds, but an agent has enough 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?

There are zero input parameters, so the baseline is 4. The description correctly adds nothing about arguments and instead spends its words on what the response contains, which is the right allocation.

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 resource — the permissions of this Nocturne connection — plus the notable field 'whether full entry text is on', which no sibling tool covers (siblings list entries, songs, timelines, entry text). It lacks an explicit verb, but the noun phrase is unambiguous enough that an agent can tell it apart from list_entries or get_entry_text.

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: an agent can infer this is the tool to call to check capabilities (e.g. whether full entry text is available) before or after fetching content. There is no explicit when-to-use statement, no exclusions, and no mention of alternatives, so the routing guidance is left to inference.

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?

Beyond the readOnlyHint, the description discloses behavior the agent could not otherwise know: the tool is disabled by default, depends on a person-enabled full-text access setting, and every read is logged and surfaced to the user. That privacy/audit context is exactly the kind of thing that should change agent behavior before calling.

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 what the tool returns, then the gating condition, then the usage restriction. No filler and nothing redundant.

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 single-parameter read tool with no output schema, the description covers purpose, opt-in gating, audit logging, and usage restriction. An agent has everything needed to decide whether to call it and how to obtain the id.

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 lone 'id' parameter has no description, only a UUID pattern. The description compensates by explaining the id's provenance ('from list_entries'), which is the main thing an agent needs to supply a valid value; it stops short of describing the failure mode for malformed or unknown ids.

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 verb and resource ('Full text of one journal entry') and ties it to the sibling that produces its input ('by id from list_entries'), so it is immediately distinguishable from list_entries and the other siblings.

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 selection rule ('Only use it when the person asks about a specific entry') and points to list_entries as the source of ids, which implicitly excludes bulk/listing use. It does not spell out fallback behavior when the person asks about an entry without having opted in, but the guidance is otherwise clear.

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 cover only readOnlyHint and openWorldHint, so the description carries the burden of describing output shape, which it does well: the aggregation fields and the rising/falling/steady trend are disclosed up front, and the explicit exclusion of journal text is a meaningful privacy signal. It stops short of stating anything about the 366-day window or behavior on empty ranges, but the schema covers the range limit.

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?

One compact sentence front-loads the resource and scope, then lists return fields in a scannable order, closing with the exclusion. No filler or redundancy.

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?

There is no output schema, so the description must describe return values — and it does so field by field, including the derived trend signal. Combined with the schema's date-range constraints and defaults, an agent has everything needed to call this 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 67%: from and to are fully documented with defaults and the 366-day limit, while bucket has only an enum and default. The description's 'grouped by day or week' explains what the bucket choice produces, but that largely restates the enum values rather than adding new 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 names a specific resource (mood) with a specific scope (date range, bucketed by day or week) and enumerates exactly what is returned: entry counts, average valence/arousal, top emotion labels, and trend direction. The closing 'No journal text' draws a hard line against text-fetching siblings such as get_entry_text.

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 journal text' implicitly routes text-seeking requests elsewhere, but no sibling is named and there is no explicit statement of when to prefer this over list_entries or get_entry_text. 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?

Annotations only declare readOnlyHint and openWorldHint, so the description must carry the return-shape burden, and it does: field list, newest-first ordering, and a privacy constraint that text is never returned. It doesn't discuss pagination behavior or what an empty range yields, which is a minor gap for a list 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 sentences, front-loaded with the resource and scope, then the return fields, then the optional filter. No filler and nothing buried.

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 five optional parameters and no output schema, the description appropriately covers what comes back and in what order, which is the key unknown. It could be slightly more complete by noting default window or pagination implications, but the schema handles those defaults.

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 80%, so the schema already documents from/to (with defaults and the 366-day cap), limit, offset, and the emotion filter. The description only restates the emotion filter's meaning and supplies one label example, adding little beyond the structured field.

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 resource (journal entries), scope (date range), ordering (newest first), and enumerates the returned fields. The line "Never returns entry text" implicitly routes the agent to get_entry_text, so it is distinguishable from its siblings 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?

Gives clear context for the common case and suggests the optional emotion filter with a concrete example ("joy"). It stops short of naming alternatives explicitly (e.g. get_mood_timeline for trend questions, get_entry_text for content), so exclusions are only implied.

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 establish readOnlyHint and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful scope information ('the song the person picked and the songs Nocturne suggested', 'Track name and artist only'), which tells the agent the result is a shallow projection rather than full song records. It doesn't mention ordering, pagination behavior, or what happens when an entry has no songs.

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?

One sentence with a colon that front-loads the resource and scope, followed by what is returned. Every clause carries information and nothing is repeated from 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?

With no output schema, the 'track name and artist only' note and the picked-vs-suggested distinction are exactly the return-value context an agent needs. Minor omissions are result ordering and behavior for entries without songs, which are low impact for a read-only list tool with fully documented parameters.

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%, with formats, defaults, the 366-day cap, and the 200 limit already documented in the schema. The description only echoes the notion of a date range and adds no syntax or edge-case guidance beyond the schema, 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 verb and resource ('Songs attached to entries in a date range') and clarifies the data source: the picked song plus Nocturne's suggestions. This is clearly distinguishable from list_entries and get_mood_timeline, though it never names a sibling 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?

Usage is implied by the date-range framing — call this when songs within a period are needed — but there is no explicit when-to-use, when-not-to-use, or pointer to alternatives such as list_entries if the caller actually wants entry text.

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